# Payment Fraud

Payment fraud is the illegal or unauthorized use or manipulation of payment instruments or transactions to obtain financial gain, goods, services, or funds.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Fandango says hackers stole payment card details from checkout pages

DevFeed: [Fandango says hackers stole payment card details from checkout pages](<https://devfeed.tech/articles/fandango-says-hackers-stole-payment-card-details-from-checkout-pages-135580.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/fandango-says-hackers-stole-payment-card-details-from-checkout-pages/>)

Author: Bill Toulas

Published: 2026-11-16T15:44:21Z

Content type: news

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [checkout](<https://devfeed.tech/tags/checkout.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [credit-card-stealer](<https://devfeed.tech/tags/credit-card-stealer.md>), [customer-data](<https://devfeed.tech/tags/customer-data.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [dark-web](<https://devfeed.tech/tags/dark-web.md>), [data-breach](<https://devfeed.tech/tags/data-breach.md>), [email](<https://devfeed.tech/tags/email.md>), [fandango](<https://devfeed.tech/tags/fandango.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [hackers](<https://devfeed.tech/tags/hackers.md>), [identity-theft](<https://devfeed.tech/tags/identity-theft.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [infosec-computer-security](<https://devfeed.tech/tags/infosec-computer-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [payment-card](<https://devfeed.tech/tags/payment-card.md>), [security](<https://devfeed.tech/tags/security.md>), [skimmer](<https://devfeed.tech/tags/skimmer.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [ticket](<https://devfeed.tech/tags/ticket.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

A checkout page skimmer exposed payment details entered on Fandango's official website from October 8-11, 2026, by sending them to hackers. The potentially affected data includes card numbers, CVVs, expiration dates, billing ZIP codes, and email addresses; Fandango says names, government IDs, SSNs, and other account information were not exposed. The company says it fixed the issue, investigated with outside specialists, and is unaware of fraud linked to the stolen data, but has not disclosed how many customers were affected. It is offering two years of IDX monitoring and recovery services, with enrollment by February 13, 2027. The excerpt advises affected customers to monitor statements and account activity and report unauthorized charges to their card issuer.

### Source excerpt

Ticket seller Fandango Media is notifying customers about a data breach that exposed payment card details entered on its checkout pages. [...]

## The Nigerian Prince Doesn't Need to Steal

DevFeed: [The Nigerian Prince Doesn't Need to Steal](<https://devfeed.tech/articles/the-nigerian-prince-doesn-t-need-to-steal-133913.md>)

Original publisher: [Read original article](<https://hackernoon.com/the-nigerian-prince-doesnt-need-to-steal?source=rss>)

Author: Peter Brauer

Published: 2026-11-13T23:23:11Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [ai alignment](<https://devfeed.tech/topics/ai-alignment.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>), [Disaster Recovery](<https://devfeed.tech/topics/disaster-recovery.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2025](<https://devfeed.tech/tags/2025.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [account](<https://devfeed.tech/tags/account.md>), [actions](<https://devfeed.tech/tags/actions.md>), [actor](<https://devfeed.tech/tags/actor.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-in-cybersecurity](<https://devfeed.tech/tags/ai-in-cybersecurity.md>), [bank](<https://devfeed.tech/tags/bank.md>), [banking](<https://devfeed.tech/tags/banking.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [cybersecurity-awareness](<https://devfeed.tech/tags/cybersecurity-awareness.md>), [defensive](<https://devfeed.tech/tags/defensive.md>), [defensive-ai](<https://devfeed.tech/tags/defensive-ai.md>), [doesn-t](<https://devfeed.tech/tags/doesn-t.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [malicious-ai](<https://devfeed.tech/tags/malicious-ai.md>), [need](<https://devfeed.tech/tags/need.md>), [nigerian-prince](<https://devfeed.tech/tags/nigerian-prince.md>), [prince](<https://devfeed.tech/tags/prince.md>), [was](<https://devfeed.tech/tags/was.md>)

### AI overview

The article argues that a bank's fraud defenses can harm customers even when they follow their assigned objective: an attacker might provoke restrictions that block legitimate access to money. It calls this "Purpose Divergence," where a narrow objective undermines the broader purpose it serves, and distinguishes that governance concern from system misalignment. Cloudflare's 2025 outage and account-lockout guidance illustrate how protective mechanisms can disrupt legitimate activity; Monzo's Stand-in shows a separate design principle of preserving essential customer functions during infrastructure failure. The author proposes measuring legitimate transactions denied or delayed alongside fraud performance, testing whether attackers can provoke disproportionate restrictions, and maintaining an accountable recovery process. These are proposed checks, not proven solutions, and the banking confrontation described is explicitly hypothetical.

### Source excerpt

When malicious AI meets defensive AI, the greatest casualty may be the human agency the bank was supposed to protect.

## CVE-2026-85632 - Unauthenticated Payment Status Manipulation in Sipay Electronic Money's WordPress (WooCommerce)

DevFeed: [CVE-2026-85632 - Unauthenticated Payment Status Manipulation in Sipay Electronic Money's WordPress (WooCommerce)](<https://devfeed.tech/articles/cve-2026-85632-unauthenticated-payment-status-manipulation-in-sipay-electronic-money-s-wordpress-woocommerce-129077.md>)

Original publisher: [Read original article](<https://cvefeed.io/vuln/detail/CVE-2026-85632>)

Author: cvefeed.io

Published: 2026-11-11T14:24:31Z

Content type: news

Language: en

Sources: [Latest High/Critical Vulnerabilitiy Feed](<https://devfeed.tech/sources/latest-high-critical-vulnerabilitiy-feed.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [WordPress](<https://devfeed.tech/topics/wordpress.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [allows](<https://devfeed.tech/tags/allows.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [authentication-bypass](<https://devfeed.tech/tags/authentication-bypass.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-85632](<https://devfeed.tech/tags/cve-2026-85632.md>), [cvss](<https://devfeed.tech/tags/cvss.md>), [details](<https://devfeed.tech/tags/details.md>), [electronic](<https://devfeed.tech/tags/electronic.md>), [function](<https://devfeed.tech/tags/function.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [money](<https://devfeed.tech/tags/money.md>), [payment](<https://devfeed.tech/tags/payment.md>), [status](<https://devfeed.tech/tags/status.md>), [woocommerce](<https://devfeed.tech/tags/woocommerce.md>), [wordpress](<https://devfeed.tech/tags/wordpress.md>)

### AI overview

CVE-2026-85632 is rated critical (9.1) and affects Sipay Electronic Money and Payment Services Inc.'s WooCommerce Virtual POS Module from version 26.8.3 to before 26.9.1. The text attributes it to missing authentication for a critical function and improper validation of an integrity check value, which may allow authentication bypass and application API message manipulation via a man-in-the-middle attack. The excerpt provides no remediation details.

### Source excerpt

CVE ID :CVE-2026-85632 Published : Nov. 11, 2026, 2:24 p.m. | 22 minutes ago Description :Missing authentication for critical function and Improper validation of integrity check value vulnerability in Sipay Electronic Money and Payment Services Inc. WooCommerce Virtual POS Module allows Authentication Bypass and Application API Message Manipulation via Man-in-the-Middle. This issue affects WooCommerce Virtual POS Module: from 26.8.3 before 26.9.1. Severity: 9.1 | CRITICAL Visit the link for more details, such as CVSS details, affected products, timeline, and more...

## How to Use IP Geolocation to Stop Bots and Fraud (Without Hurting UX)

DevFeed: [How to Use IP Geolocation to Stop Bots and Fraud (Without Hurting UX)](<https://devfeed.tech/articles/how-to-use-ip-geolocation-to-stop-bots-and-fraud-without-hurting-ux-130704.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/how-to-use-ip-geolocation-to-stop-bots-and-fraud-without-hurting-ux/>)

Author: SitePoint Team

Published: 2026-11-11T12:23:33Z

Content type: article

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [Bot Management](<https://devfeed.tech/topics/bot-management.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>)

Tags: [2fa](<https://devfeed.tech/tags/2fa.md>), [403](<https://devfeed.tech/tags/403.md>), [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [api](<https://devfeed.tech/tags/api.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bots](<https://devfeed.tech/tags/bots.md>), [cache](<https://devfeed.tech/tags/cache.md>), [captchas](<https://devfeed.tech/tags/captchas.md>), [checkout](<https://devfeed.tech/tags/checkout.md>), [credential-stuffing](<https://devfeed.tech/tags/credential-stuffing.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [device](<https://devfeed.tech/tags/device.md>), [digital-trust](<https://devfeed.tech/tags/digital-trust.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [geolocation](<https://devfeed.tech/tags/geolocation.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [ip](<https://devfeed.tech/tags/ip.md>), [security](<https://devfeed.tech/tags/security.md>), [ux](<https://devfeed.tech/tags/ux.md>), [web-security](<https://devfeed.tech/tags/web-security.md>)

### AI overview

IP geolocation can provide risk signals for bot and fraud detection while keeping friction proportional to risk. The excerpt recommends checking location alongside ASN, connection type, proxy or VPN indicators, timezone, and a user's usual countries, networks, and login hours; anomalies such as data-center traffic, signup bursts, impossible travel, or timezone mismatches should raise a score, not automatically prove fraud. Its soft geo-fencing approach allows low-risk activity, prompts medium-risk users for step-up authentication, applies stronger checks or review at high risk, and blocks confirmed abuse. For Express.js, it suggests short-timeout lookups, trusting only owned proxies, caching results, scoring warning signs, and applying checks to sensitive routes. VPNs, travel, and mobile networks can cause false alarms, so geolocation works best with other signals.

### Source excerpt

null Continue reading How to Use IP Geolocation to Stop Bots and Fraud (Without Hurting UX) on SitePoint.

## Three People Arrested for AI-Enhanced Impersonation Fraud

DevFeed: [Three People Arrested for AI-Enhanced Impersonation Fraud](<https://devfeed.tech/articles/three-people-arrested-for-ai-enhanced-impersonation-fraud-129235.md>)

Original publisher: [Read original article](<https://www.schneier.com/blog/archives/2026/11/three-people-arrested-for-ai-enhanced-impersonation-fraud.html>)

Author: Bruce Schneier

Published: 2026-11-11T12:05:34Z

Content type: news

Language: en

Sources: [Schneier on Security](<https://devfeed.tech/sources/schneier-on-security.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-security](<https://devfeed.tech/tags/ai-and-security.md>), [arrested](<https://devfeed.tech/tags/arrested.md>), [cybercrime](<https://devfeed.tech/tags/cybercrime.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [identity-theft](<https://devfeed.tech/tags/identity-theft.md>), [impersonation](<https://devfeed.tech/tags/impersonation.md>), [law-enforcement](<https://devfeed.tech/tags/law-enforcement.md>), [scams](<https://devfeed.tech/tags/scams.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>)

### AI overview

According to the U.S. attorney's office for the Southern District of New York, three men allegedly used AI-altered voices and images to impersonate corporate executives, direct employees to contact lawyers, and then pose as those lawyers to induce large wire transfers. The alleged scheme ran from 2024 to 2026 and stole more than $129 million from companies worldwide, including in the U.S. Two suspects were arrested in Spain and one in the U.K.

### Source excerpt

It's hard to believe how lucrative this crime can be: According to a press release from the United States attorney's office for the southern district of New York, three men  Jacob Soall, Sharon Hazan, and Guy Sheetrit  were arrested for using AI to alter and impersonate the voices and images of executives and attorneys at various companies in order to convince employees to send over large payments. Soall and Hazan were arrested in Spain over the summer, while Sheetrit was arrested in the United Kingdom in September. The alleged fraud took place between 2024 and 2026...

## Nacha Rules Explained: What Businesses Accepting ACH Must Follow

DevFeed: [Nacha Rules Explained: What Businesses Accepting ACH Must Follow](<https://devfeed.tech/articles/nacha-rules-explained-what-businesses-accepting-ach-must-follow-127012.md>)

Original publisher: [Read original article](<https://dodopayments.com/blogs/nacha-rules/>)

Author: Deepak Jangir

Published: 2026-11-10T00:00:00Z

Content type: article

Language: en

Sources: [Dodo Payments Blog](<https://devfeed.tech/sources/dodo-payments-blog.md>)

Topics: [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Finance](<https://devfeed.tech/topics/finance.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ach](<https://devfeed.tech/tags/ach.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [limits](<https://devfeed.tech/tags/limits.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [payments](<https://devfeed.tech/tags/payments.md>), [return](<https://devfeed.tech/tags/return.md>), [rules](<https://devfeed.tech/tags/rules.md>), [sec](<https://devfeed.tech/tags/sec.md>)

### AI overview

Businesses that originate ACH debits must follow Nacha rules through their bank or payment provider. Key duties include using the correct SEC code (typically WEB for consumer online debits and CCD for business debits), obtaining clear authorization, retaining it for two years after termination or revocation, validating WEB debit accounts on first use and account changes, and monitoring returns and reinitiation limits. Unauthorized consumer debits may be returned for up to 60 days; return thresholds can trigger bank inquiries and enforcement. The 2026 risk rules extend risk based fraud monitoring to covered parties for debits and credits, with annual review. Account numbers must be encrypted in transit; covered originators and processors above two million entries yearly must also render stored numbers unreadable. The article says a merchant of record that originates entries carries most network facing obligations, while merchants still have operational duties. Its Dodo example supports one time USD ACH payments, with settlement taking up to four business days and fulfillment advised only after a succeeded webhook.

### Source excerpt

Nacha rules govern every ACH debit. Learn the operating rules for merchants: SEC codes, authorizations, return rate limits and 2026 fraud monitoring updates.

## Payment Reversal: Voids, Refunds, and Chargebacks Explained

DevFeed: [Payment Reversal: Voids, Refunds, and Chargebacks Explained](<https://devfeed.tech/articles/payment-reversal-voids-refunds-and-chargebacks-explained-127013.md>)

Original publisher: [Read original article](<https://dodopayments.com/blogs/payment-reversal/>)

Author: Deepak Jangir

Published: 2026-11-10T00:00:00Z

Content type: article

Language: en

Sources: [Dodo Payments Blog](<https://devfeed.tech/sources/dodo-payments-blog.md>)

Topics: [Finance](<https://devfeed.tech/topics/finance.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [payment-gateway](<https://devfeed.tech/topics/payment-gateway.md>)

Tags: [ach](<https://devfeed.tech/tags/ach.md>), [chargebacks](<https://devfeed.tech/tags/chargebacks.md>), [cost](<https://devfeed.tech/tags/cost.md>), [impact](<https://devfeed.tech/tags/impact.md>), [payment](<https://devfeed.tech/tags/payment.md>), [payments](<https://devfeed.tech/tags/payments.md>), [refunds](<https://devfeed.tech/tags/refunds.md>), [timing](<https://devfeed.tech/tags/timing.md>), [voids](<https://devfeed.tech/tags/voids.md>)

### AI overview

Payment reversals differ by settlement status and who initiates them: voids cancel unsettled authorizations, refunds return settled funds at the merchant's request, card chargebacks are issuer-driven disputes, and ACH payments can be returned by the customer's bank. Voids usually avoid fees, while refunds create a new credit and chargebacks add a dispute fee, staff work, and dispute-ratio impact. Issuers control how quickly a void's pending hold disappears. The excerpt says Dodo Payments supports full or partial refunds to the original method, requires a refund reason, and charges $1 per refund; ACH Direct Debit should be fulfilled only after `payment.succeeded`. It recommends quick voluntary refunds, recognizable statement descriptors, and pre-dispute alerts to prevent chargebacks, while noting their listed Dodo fees ($18 for Visa RDR, $27 for Ethoca alerts, $15 for dispute deflections) apply when they stop a dispute.

### Source excerpt

A payment reversal sends money back to the cardholder. Learn how voids, refunds, chargebacks and ACH returns differ in timing, cost and dispute impact.

## Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection

DevFeed: [Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection](<https://devfeed.tech/articles/dual-stream-llm-guided-reward-design-for-reject-inference-aware-reinforcement-learning-in-e-commerce-payment-fraud-detection-123296.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08706>)

Author: Bo Qu, Zhurong Wang, Frank Zahradnik, Ming Ouyang

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [learning](<https://devfeed.tech/tags/learning.md>), [llm](<https://devfeed.tech/tags/llm.md>), [payment](<https://devfeed.tech/tags/payment.md>), [payment-fraud](<https://devfeed.tech/tags/payment-fraud.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [stream](<https://devfeed.tech/tags/stream.md>)

### AI overview

The dual-stream reward design targets bias from fraud transactions blocked by a legacy system, which therefore lack fraud labels. A single LLM evolves a reward for the existing two-step REINFORCE blocking policy: one stream applies dollar-weighted precision to labeled transactions; the other scores legacy-blocked transactions by contrasting a newer gradient-boosted risk signal with the legacy scores used to block them. The LLM chooses among exposed evidence using evaluation feedback, and its reward code makes that choice auditable. On a held-out four-month out-of-time test, it exceeded the labeled-only agent's dollar-weighted precision by 4.7, 2.4, and 3.0 points at 80%, 85%, and 90% recall, respectively, and beat the production baseline by 6.8 points on average. The resulting policy adds no inference cost.

### Source excerpt

arXiv:2611.08706v1 Announce Type: new Abstract: Production fraud-detection models learn from a censored slice of their own traffic: transactions a legacy system blocked never receive fraud labels, so models train on a biased, approved-only distribution. We extend LLM-guided reward design, the framework of Qu et al. (2025) in which an LLM evolves the reward of a two-step REINFORCE fraud-blocking policy, to attack this reject-inference problem inside the reward. A single LLM designs a dual-stream reward: stream 1 applies the standard dollar-weighted precision objective to labeled transactions; stream 2 scores legacy-blocked, unlabeled transactions by contrasting the newest gradient-boosted risk signal against the legacy scores that drove the original block. Rather than prescribe which signals matter, we expose a superset of evidence and let the LLM decide for itself which to use, guided by evaluation feedback alone; because it writes the reward as code, that choice is directly auditable. On a held-out four-month out-of-time test, the dual-stream agent beats the prior labeled-only agent at every target recall, by +4.7, +2.4 and +3.0 points of dollar-weighted precision at 80%, 85% and 90% recall, and the production baseline by +6.8 points on average. The resulting policy is architecturally identical to that of Qu et al. (2025) and adds no inference cost.

## LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection

DevFeed: [LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection](<https://devfeed.tech/articles/llm-enhanced-self-evolving-reinforcement-learning-for-multi-step-e-commerce-payment-fraud-risk-detection-124355.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.18719>)

Author: Bo Qu, Zhurong Wang, Daisuke Yagi, Zhen Xu, Yang Zhao, Yinan Shan, Frank Zahradnik

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [commerce](<https://devfeed.tech/tags/commerce.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [learning](<https://devfeed.tech/tags/learning.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [markov](<https://devfeed.tech/tags/markov.md>), [payment](<https://devfeed.tech/tags/payment.md>), [payment-fraud](<https://devfeed.tech/tags/payment-fraud.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [risk](<https://devfeed.tech/tags/risk.md>), [rl](<https://devfeed.tech/tags/rl.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

The paper frames e-commerce payment risk detection as a multi-step Markov Decision Process, using reinforcement learning to assess transactions across payment stages. It uses LLMs to iteratively refine the reward functions that guide the RL system, a task the abstract says typically requires substantial human expertise. The abstract reports improved fraud detection accuracy and zero-shot capability, with long-term evaluations on real-world data described as showing effectiveness, robustness, and resilience. It provides no quantitative results or details of the evaluation.

### Source excerpt

arXiv:2509.18719v1 Announce Type: cross Abstract: This paper presents a novel approach to e-commerce payment fraud detection by integrating reinforcement learning (RL) with Large Language Models (LLMs). By framing transaction risk as a multi-step Markov Decision Process (MDP), RL optimizes risk detection across multiple payment stages. Crafting effective reward functions, essential for RL model success, typically requires significant human expertise due to the complexity and variability in design. LLMs, with their advanced reasoning and coding capabilities, are well-suited to refine these functions, offering improvements over traditional methods. Our approach leverages LLMs to iteratively enhance reward functions, achieving better fraud detection accuracy and demonstrating zero-shot capability. Experiments with real-world data confirm the effectiveness, robustness, and resilience of our LLM-enhanced RL framework through long-term evaluations, underscoring the potential of LLMs in advancing industrial RL applications.

## Closing the context gap is what banking AI needs

DevFeed: [Closing the context gap is what banking AI needs](<https://devfeed.tech/articles/closing-the-context-gap-is-what-banking-ai-needs-121858.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/data-strategy/closing-the-context-gap-is-what-banking-ai-needs>)

Author: Rav Hayer

Published: 2026-11-06T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [context](<https://devfeed.tech/topics/context.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Finance](<https://devfeed.tech/topics/finance.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bank](<https://devfeed.tech/tags/bank.md>), [banking](<https://devfeed.tech/tags/banking.md>), [blueprint](<https://devfeed.tech/tags/blueprint.md>), [budget](<https://devfeed.tech/tags/budget.md>), [context](<https://devfeed.tech/tags/context.md>), [credit-card](<https://devfeed.tech/tags/credit-card.md>), [credit-risk](<https://devfeed.tech/tags/credit-risk.md>), [credit-scoring](<https://devfeed.tech/tags/credit-scoring.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [demo](<https://devfeed.tech/tags/demo.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [developer](<https://devfeed.tech/tags/developer.md>), [digital](<https://devfeed.tech/tags/digital.md>)

### AI overview

The article attributes the gap between banking AI pilots and production to missing transaction context, not primarily to model quality. General-purpose language models lack native understanding of transactions, while transaction foundation models are trained on transaction events; it cites examples and reported results from Mastercard, Revolut and Stripe. Rebuilding customer and transaction context separately for each pilot adds cost and inconsistency, so the article describes a shared intelligence layer trained on an institution's history for fraud, credit risk, payments and customer experience. It also reports a hybrid strategy: frontier models for complex reasoning and smaller, fine-tuned models for narrow tasks near sensitive data. This requires governance from the outset, including records of prompts and answers, access limits and reconstructable decisions. A financial loss can make the case for moving a use case from proof of concept to deployment.

### Source excerpt

Closing the context gap is what banking AI needs

## Why a language model misses fraud in your transaction data

DevFeed: [Why a language model misses fraud in your transaction data](<https://devfeed.tech/articles/why-a-language-model-misses-fraud-in-your-transaction-data-121859.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/why-a-language-model-misses-fraud-in-your-transaction-data>)

Author: Nathan Hilt

Published: 2026-11-06T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [audit trail](<https://devfeed.tech/topics/audit-trail.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [adyen](<https://devfeed.tech/tags/adyen.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [aws](<https://devfeed.tech/tags/aws.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [context](<https://devfeed.tech/tags/context.md>), [context-layer](<https://devfeed.tech/tags/context-layer.md>), [credit-card](<https://devfeed.tech/tags/credit-card.md>), [customer](<https://devfeed.tech/tags/customer.md>), [data](<https://devfeed.tech/tags/data.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [model](<https://devfeed.tech/tags/model.md>), [transaction](<https://devfeed.tech/tags/transaction.md>)

### AI overview

Transaction foundation models (TFMs) and graph neural networks (GNNs) address different fraud patterns: TFMs learn behavioral and temporal patterns in one entity's transaction history, while GNNs use relationships among customers, devices, merchants and cards to detect coordinated activity. The text says they can complement each other in a shared context layer. It describes structuring data with consistent semantic definitions and says AWS typically recommends 25 months of historical data to get started. A cited demonstration using Claude produced vague flags on raw transactions and a structured risk breakdown when grounded in transaction context. For production, the article recommends building an audit trail, access limits and decision reconstruction into the pipeline. Market examples include reported results from Revolut and Adyen; these are presented as company-reported proof points.

### Source excerpt

Why a language model misses fraud in your transaction data

## What Is a BIN Number? Bank Identification Numbers Explained

DevFeed: [What Is a BIN Number? Bank Identification Numbers Explained](<https://devfeed.tech/articles/what-is-a-bin-number-bank-identification-numbers-explained-119305.md>)

Original publisher: [Read original article](<https://dodopayments.com/blogs/bin-number/>)

Author: Deepak Jangir

Published: 2026-11-05T00:00:00Z

Content type: article

Language: en

Sources: [Dodo Payments Blog](<https://devfeed.tech/sources/dodo-payments-blog.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [payment-gateway](<https://devfeed.tech/topics/payment-gateway.md>), [Finance](<https://devfeed.tech/topics/finance.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2022](<https://devfeed.tech/tags/2022.md>), [3](<https://devfeed.tech/tags/3.md>), [3d](<https://devfeed.tech/tags/3d.md>), [about](<https://devfeed.tech/tags/about.md>), [acceptance](<https://devfeed.tech/tags/acceptance.md>), [account](<https://devfeed.tech/tags/account.md>), [ach](<https://devfeed.tech/tags/ach.md>), [bank](<https://devfeed.tech/tags/bank.md>), [card](<https://devfeed.tech/tags/card.md>), [data](<https://devfeed.tech/tags/data.md>), [first](<https://devfeed.tech/tags/first.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [fraud-prevention](<https://devfeed.tech/tags/fraud-prevention.md>), [number](<https://devfeed.tech/tags/number.md>), [numbers](<https://devfeed.tech/tags/numbers.md>), [payment](<https://devfeed.tech/tags/payment.md>), [payment-card](<https://devfeed.tech/tags/payment-card.md>), [payments](<https://devfeed.tech/tags/payments.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [routing](<https://devfeed.tech/tags/routing.md>), [what-is](<https://devfeed.tech/tags/what-is.md>)

### AI overview

A BIN/IIN is the first 6 to 8 digits of a card number; it identifies the issuer and provides card attributes such as network, funding type, product level, and issuing country, but not the cardholder's identity or account details. Merchants use these attributes for fraud screening, subscription and trial risk, payment routing, fee assessment, and US debit versus credit surcharging. The shift to 8-digit BINs means older six-digit rules and lookup databases can misclassify cards; merchants should keep data current and check provider truncation formats. BIN signals are not proof of fraud: combining them with other signals can guide added scrutiny, while hard blocks may reject legitimate users. Hosted or tokenizing payment providers can return BIN-derived attributes without exposing raw card numbers.

### Source excerpt

A BIN number is the first 6 to 8 digits of a payment card. Learn what BINs reveal, the move to 8-digit BINs, and how merchants use BIN data for fraud, routing and pricing.

## Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning

DevFeed: [Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning](<https://devfeed.tech/articles/reconstructing-fraudulent-strategies-in-online-payments-via-interpretable-inverse-reinforcement-learning-117534.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04819>)

Author: Huilin He, Weiyu Han, Linbo Shao, Ruobing Zuo, Xiao Tan, Shuai Chen, Dawei Cheng

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [payment-fraud](<https://devfeed.tech/tags/payment-fraud.md>), [payments](<https://devfeed.tech/tags/payments.md>), [policies](<https://devfeed.tech/tags/policies.md>), [policy](<https://devfeed.tech/tags/policy.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [security](<https://devfeed.tech/tags/security.md>), [sequence](<https://devfeed.tech/tags/sequence.md>)

### AI overview

PaySeqGen reconstructs fraud behavior policies from observed payment trajectories to generate sequentially plausible fraud samples for detector augmentation and to support analysis of fraud patterns. Its candidate-action mechanism enables plausible sequence generation and exploration; alternating reward learning with policy optimization captures interpretable preferences across transaction contexts. In real-world scenarios at Ant International, the authors report that it outperforms state-of-the-art generative augmentation methods, and that reward-based analysis helps analysts locate suspicious segments and examine multistep tactics. The abstract also reports effectiveness in a deployed online payment system, without specifying metrics or deployment details.

### Source excerpt

arXiv:2611.04819v1 Announce Type: new Abstract: Payment fraud causes financial losses and undermines users' trust in web payment services. Although fraud detection is a critical defense for payment security, complex and diverse fraudulent behaviors can still evade detection. Generating fraud samples for data augmentation can broaden detectors' coverage of different fraud patterns. However, existing methods matching the distribution of transaction attributes alone do not ensure that generated sequences preserve the sequential relationships among transaction choices, payment feedback, and subsequent behavioral adjustments. To this end, we propose PaySeqGen, an interpretable inverse reinforcement learning framework that reconstructs fraud behavior policies from fraudsters' observed payment trajectories. We design a mechanism for constructing candidate actions to support plausible payment sequence generation while enabling exploration. The framework also learns interpretable behavioral rewards that capture fraudsters' preferences across different transaction contexts. By alternating between reward learning and policy optimization, the framework reconstructs policies that generate new fraud sequences for detector augmentation and learns interpretable rewards supporting sequential fraud-pattern analysis in real trajectories. Experiments in real-world payment scenarios at Ant International, a leading global digital payment provider, show that PaySeqGen outperforms state-of-the-art generative augmentation methods. Reward-based trajectory analysis also identifies fraud patterns of practical value, helping analyst locating suspicious segments and examine multistep fraud tactics. Evaluation in the deployed system of online payment further confirms its effectiveness.

## InterFuse: Interaction-Guided Adaptive Fusion of Heterogeneous Models for Payment Risk Ranking

DevFeed: [InterFuse: Interaction-Guided Adaptive Fusion of Heterogeneous Models for Payment Risk Ranking](<https://devfeed.tech/articles/interfuse-interaction-guided-adaptive-fusion-of-heterogeneous-models-for-payment-risk-ranking-115342.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02640>)

Author: Haoyu Jiang, Weiyu Han, Ze Zhao, Jie Sheng, Ruobing Zuo, Xiao Tan, Shuai Chen, Tianyi Zhang

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [models](<https://devfeed.tech/tags/models.md>), [payment](<https://devfeed.tech/tags/payment.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [risk](<https://devfeed.tech/tags/risk.md>)

### AI overview

InterFuse uses cross-model interactions to guide transaction-specific aggregation of payment risk models. It encodes each model's representation, prediction score, and input coverage as a token, represents unavailable outputs with learned states, and applies availability-aware attention to form a shared fusion state. That state guides aggregation across available models using their updated representations, original predictions, and coverage. On an industrial payment replay and three public financial benchmarks, with the same upstream models across fusion methods, InterFuse achieved the highest top-ranked recall and AUC on all four datasets; Recall@1% improved by 1.11-8.09 percentage points over the strongest baselines. Ablations support the contributions of cross-model interaction and adaptive aggregation. Industrial analyses found larger interaction gains when predictions disagreed. The abstract also reports analyses of missing-output robustness and the trade-off between ranking gains and fusion latency, without detailing their results.

### Source excerpt

arXiv:2611.02640v1 Announce Type: new Abstract: Payment platforms use view-specific models trained on transaction attributes, behavioral histories, and relational structures to rank transactions under limited review budgets. However, existing fusion methods often focus on prediction scores or interactions among model representations, with less attention to how these interactions should guide aggregation using each model's original prediction and input coverage. To address this limitation, we propose InterFuse, a fusion framework that uses a shared fusion state from cross-model interaction to guide transaction-adaptive aggregation. InterFuse encodes each model's representation, prediction score, and input coverage as a model-specific token, using learned states for unavailable outputs. Availability-aware attention updates these tokens and produces a shared fusion state. This state then guides aggregation over available models using their updated representations, original predictions, and input coverage. We evaluate InterFuse on an industrial payment replay and three public financial benchmarks using the same upstream models across fusion methods. InterFuse achieves the highest top-ranked recall and AUC on all four datasets, improving Recall@1% by 1.11-8.09 percentage points over the strongest baselines. Ablations show the benefits of cross-model interaction and adaptive aggregation, while industrial analyses find larger interaction gains when model predictions disagree. Additional analyses examine robustness to missing outputs and the trade-off between ranking gains and fusion latency.

## Improving Financial Cybersecurity Through Fraud Transaction Detection with Deep Learning

DevFeed: [Improving Financial Cybersecurity Through Fraud Transaction Detection with Deep Learning](<https://devfeed.tech/articles/improving-financial-cybersecurity-through-fraud-transaction-detection-with-deep-learning-114682.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02312>)

Author: Harish Kant Pathak, Rahul Kumar

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [detection](<https://devfeed.tech/tags/detection.md>), [financial-fraud](<https://devfeed.tech/tags/financial-fraud.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>)

### AI overview

The paper evaluates LSTM, CNN, and hybrid deep learning models for detecting anomalous financial transactions, reporting improvements over conventional machine learning baselines on real-world transaction datasets. It says the approach aims to detect fraud while minimizing false positives and to scale for enterprise cybersecurity. The excerpt does not specify datasets, metrics, or comparative results for individual architectures.

### Source excerpt

arXiv:2611.02312v1 Announce Type: new Abstract: Financial fraud detection remains a critical challenge in cybersecurity, with traditional rule-based systems struggling to keep pace with evolving attack patterns. This paper presents a deep learning approach for fraud transaction detection, leveraging neural network architectures to identify anomalous financial behaviors with high accuracy. We evaluate multiple deep learning models including LSTM, CNN, and hybrid architectures on real-world financial transaction datasets, demonstrating significant improvements over conventional machine learning baselines. Our approach achieves robust performance in detecting fraudulent transactions while minimizing false positives, providing a scalable solution for enterprise financial cybersecurity systems

## Unmasking fraud networks: How graph-grounded Copilots stop P2P fraud in Microsoft Fabric

DevFeed: [Unmasking fraud networks: How graph-grounded Copilots stop P2P fraud in Microsoft Fabric](<https://devfeed.tech/articles/unmasking-fraud-networks-how-graph-grounded-copilots-stop-p2p-fraud-in-microsoft-fabric-108431.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/unmasking-fraud-neo4j-in-microsoft-fabric/>)

Author: Keaton Crowe

Published: 2026-10-30T15:43:30Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [multi-accounting fraud](<https://devfeed.tech/topics/multi-accounting-fraud.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Purview](<https://devfeed.tech/topics/purview.md>), [Azure](<https://devfeed.tech/topics/azure.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [azure](<https://devfeed.tech/tags/azure.md>), [banks](<https://devfeed.tech/tags/banks.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [device](<https://devfeed.tech/tags/device.md>), [fabric](<https://devfeed.tech/tags/fabric.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [ip](<https://devfeed.tech/tags/ip.md>), [microsoft-fabric](<https://devfeed.tech/tags/microsoft-fabric.md>), [networks](<https://devfeed.tech/tags/networks.md>), [p2p](<https://devfeed.tech/tags/p2p.md>), [transactions](<https://devfeed.tech/tags/transactions.md>)

### AI overview

The excerpt describes a Microsoft Fabric and Neo4j approach to P2P fraud investigations: OneLake consolidates data in Delta tables, Neo4j turns those tables into property graphs, and graph algorithms help distinguish strong links from noisy shared infrastructure. Relational joins can treat a shared private card and a public Wi-Fi IP alike, creating many false leads. Neo4j can filter high-traffic hubs, focus on rare identifiers and payment paths, and use Graph Data Science algorithms such as Weakly Connected Components to group strongly connected accounts. In the example, accounts A-102, A-104, A-106, and A-107 are grouped with fraudulent A-101, while A-103 is excluded based only on shared coffee shop Wi-Fi. The resulting graph metrics can be written to OneLake for Fabric Data Agents and Copilots to query with network context. The excerpt also names Fabric governance features and describes enabling Neo4j through the Workload Hub or Azure Marketplace.

### Source excerpt

Every second, financial networks log millions of data points across disconnected internal systems: debit transactions, peer-to-peer (P2P) transfers, device fingerprints, phone numbers, and IP addresses. But when organized crime rings strike, standard relational databases hit a wall trying to trace... Read more ->

## How to Detect Financial Fraud Patterns with Knowledge Graphs: A Production Guide

DevFeed: [How to Detect Financial Fraud Patterns with Knowledge Graphs: A Production Guide](<https://devfeed.tech/articles/how-to-detect-financial-fraud-patterns-with-knowledge-graphs-a-production-guide-109749.md>)

Original publisher: [Read original article](<https://www.freecodecamp.org/news/how-to-detect-financial-fraud-patterns-with-knowledge-graphs-a-production-guide/>)

Author: Kamal Kishore

Published: 2026-10-30T13:57:52Z

Content type: tutorial

Language: en

Sources: [Free Code Camp](<https://devfeed.tech/sources/freecodecamp-programming-tutorials-python-javascript-git-more.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [finance](<https://devfeed.tech/tags/finance.md>), [financial](<https://devfeed.tech/tags/financial.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [guide](<https://devfeed.tech/tags/guide.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [production](<https://devfeed.tech/tags/production.md>)

### AI overview

The guide presents Neo4j knowledge graphs as a way to detect coordinated payment fraud that isolated transaction rules may miss. It models vendors, invoices, payments, employees, organizations and bank accounts, then materializes shared-account, location and routing-prefix links to trade some ingestion latency for faster runtime queries. Parameterized Cypher queries target duplicate invoices, circular schemes, mule accounts, vendor collusion and out-of-jurisdiction approvals. A reproducible synthetic dataset and ground-truth manifest support recall checks; the reported results include 100% recall for several injected patterns, but 89 vendors flagged for collusion and the examples do not establish production performance. For scaling, the guide recommends synchronous bounded deterministic checks followed by asynchronous graph-feature scoring, threshold tuning from analyst feedback, and controls for high-degree legitimate entities. It also notes requirements including Python 3.10+, Docker Compose and Neo4j.

### Source excerpt

Most anti-fraud architectures in enterprise payment workflows evaluate transactions in isolation. When an invoice arrives, an automated rules engine checks it against static thresholds. It checks whet

## Scammers rebuild fake shopping sites within hours of a takedown

DevFeed: [Scammers rebuild fake shopping sites within hours of a takedown](<https://devfeed.tech/articles/scammers-rebuild-fake-shopping-sites-within-hours-of-a-takedown-107286.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/10/30/akamai-fake-account-abuse-report/>)

Author: Anamarija Pogorelec

Published: 2026-10-30T05:30:26Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [fake account fraud](<https://devfeed.tech/topics/fake-account-fraud.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [account-hijacking](<https://devfeed.tech/tags/account-hijacking.md>), [akamai](<https://devfeed.tech/tags/akamai.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [card](<https://devfeed.tech/tags/card.md>), [checkout](<https://devfeed.tech/tags/checkout.md>), [collection](<https://devfeed.tech/tags/collection.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [designs](<https://devfeed.tech/tags/designs.md>), [domains](<https://devfeed.tech/tags/domains.md>), [event](<https://devfeed.tech/tags/event.md>), [fake](<https://devfeed.tech/tags/fake.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [hospitality](<https://devfeed.tech/tags/hospitality.md>), [html](<https://devfeed.tech/tags/html.md>), [information](<https://devfeed.tech/tags/information.md>), [ip](<https://devfeed.tech/tags/ip.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [look](<https://devfeed.tech/tags/look.md>), [news](<https://devfeed.tech/tags/news.md>), [rebuild](<https://devfeed.tech/tags/rebuild.md>), [report](<https://devfeed.tech/tags/report.md>), [scams](<https://devfeed.tech/tags/scams.md>), [shopping](<https://devfeed.tech/tags/shopping.md>), [sites](<https://devfeed.tech/tags/sites.md>), [takedown](<https://devfeed.tech/tags/takedown.md>)

### AI overview

A retail scam used more than 1,200 look-alike .shop domains on one IP address, reusing site code and checkout designs to send payment details to a shared collection system. Similar ticket sites also sought personal information, sometimes including passport or identity-document details. Multiple domains, dormant registrations, visitor-specific pages, compromised websites and reused phishing kits let operators replace sites within hours of takedowns. The article also describes malicious apps promoted through social ads, fake recruitment forms, credential stuffing against reused passwords, and fraudulent account creation for bonuses, stolen-card testing or stock hoarding. In Akamai's 30-day July-August 2026 sample, 26.6% of login attempts were classified as high or critical risk; account verification requests made up 40% of that risky traffic.

### Source excerpt

One retail scam used more than 1,200 look-alike .shop domains sharing a single IP address. The sites reused HTML, JavaScript and payment-page designs intended to harvest card numbers, expiry dates and security codes, according Akamai's Fraud and Abuse Report 2026. A ticket scam used a similar setup. Several websites impersonating official ticketing and hospitality portals for a major sporting event were designed to route payment and personal information to the same collection system. Some checkout ... More -> The post Scammers rebuild fake shopping sites within hours of a takedown appeared first on Help Net Security.

## Hackers hijack Convertr analytics script to steal payment card data

DevFeed: [Hackers hijack Convertr analytics script to steal payment card data](<https://devfeed.tech/articles/hackers-hijack-convertr-analytics-script-to-steal-payment-card-data-102563.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/hackers-hijack-convertr-analytics-script-to-steal-payment-card-data/>)

Author: Bill Toulas

Published: 2026-10-27T20:57:25Z

Content type: news

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [api](<https://devfeed.tech/tags/api.md>), [bank](<https://devfeed.tech/tags/bank.md>), [brazil](<https://devfeed.tech/tags/brazil.md>), [cache](<https://devfeed.tech/tags/cache.md>), [caching](<https://devfeed.tech/tags/caching.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [card](<https://devfeed.tech/tags/card.md>), [checkout](<https://devfeed.tech/tags/checkout.md>), [cleanup](<https://devfeed.tech/tags/cleanup.md>), [commerce](<https://devfeed.tech/tags/commerce.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [credit-card](<https://devfeed.tech/tags/credit-card.md>), [credit-card-stealer](<https://devfeed.tech/tags/credit-card-stealer.md>), [data](<https://devfeed.tech/tags/data.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [hackers](<https://devfeed.tech/tags/hackers.md>), [hijack](<https://devfeed.tech/tags/hijack.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [infosec-computer-security](<https://devfeed.tech/tags/infosec-computer-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [magecart](<https://devfeed.tech/tags/magecart.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [payment](<https://devfeed.tech/tags/payment.md>), [payment-card](<https://devfeed.tech/tags/payment-card.md>), [platform](<https://devfeed.tech/tags/platform.md>), [script](<https://devfeed.tech/tags/script.md>), [security](<https://devfeed.tech/tags/security.md>), [skimmer](<https://devfeed.tech/tags/skimmer.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>), [supply-chain-attack](<https://devfeed.tech/tags/supply-chain-attack.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

Sansec reports that attackers injected a payment skimmer into Convertr's self-hosted Plausible analytics tracker, which loads on checkout pages across its merchant platform. The code collected card numbers, expiration dates, CVVs, cardholder names and CPF taxpayer IDs; by October 26, it had been tailored to Convertr's payment API field names. Sansec suspects, but has not confirmed, exploitation of CVE-2026-8467 in an outdated Plausible Community Edition installation. Convertr removed the skimmer, upgraded Plausible and said it was notifying affected merchants and payment providers. Sansec warns browser caching could keep the script active for up to 24 hours after cleanup. It advises people who paid by card since October 24 on Brazilian stores with "checkout.convertr" in the checkout address to contact their bank and block the card, and to clear their browser cache before ordering again.

### Source excerpt

A credit card skimming group reportedly compromised a shared analytics script used by e-commerce platform Convertr to steal shoppers' payment data during checkout. [...]

## Fraud is Getting Faster, Thanks to AI

DevFeed: [Fraud is Getting Faster, Thanks to AI](<https://devfeed.tech/articles/fraud-is-getting-faster-thanks-to-ai-101095.md>)

Original publisher: [Read original article](<https://sdtimes.com/mobile-security/fraud-is-getting-faster-thanks-to-ai/>)

Author: Jason Cortlund

Published: 2026-10-26T17:53:40Z

Content type: article

Language: en

Sources: [SD Times](<https://devfeed.tech/sources/sd-times.md>)

Topics: [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [account takeover](<https://devfeed.tech/topics/account-takeover.md>), [obfuscation](<https://devfeed.tech/topics/obfuscation.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [known exploitable vulnerabilities](<https://devfeed.tech/topics/known-exploitable-vulnerabilities.md>)

Tags: [account-takeover](<https://devfeed.tech/tags/account-takeover.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-assisted-reverse-engineering](<https://devfeed.tech/tags/ai-assisted-reverse-engineering.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [api](<https://devfeed.tech/tags/api.md>), [api-security](<https://devfeed.tech/tags/api-security.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [banking](<https://devfeed.tech/tags/banking.md>), [email](<https://devfeed.tech/tags/email.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [polymorphism](<https://devfeed.tech/tags/polymorphism.md>), [sms](<https://devfeed.tech/tags/sms.md>), [text](<https://devfeed.tech/tags/text.md>), [transactions](<https://devfeed.tech/tags/transactions.md>)

### AI overview

The excerpt describes AI as speeding up mobile fraud through automation and scale, while focusing on four attack paths: credential theft aided by reverse engineering, automated phishing and malware, deepfake injection into identity checks, and agentic bots targeting APIs. It cites increased SMS and text approaches, account takeover attempts, biometric spoofing, and API attacks, alongside examples of malware using AI integrations. Recommended defenses include continuous mobile app security testing aligned with OWASP, code hardening and runtime tamper checks, polymorphic protections that vary across releases, and app attestation with real-time threat monitoring to restrict API access to legitimate apps in trusted environments. The excerpt emphasizes that security measures should preserve development speed, app performance, and user experience.

### Source excerpt

A growing population of consumers around the world prefers mobile transactions for retail purchases, banking, and a wide range of services. Fraudsters have kept pace with the "mobile-first" trend. A new PYMNTS report shows that initial contact for fraud attacks via SMS and text grew 35% since September 2025, while email approaches fell by 30%.... ... continue reading The post Fraud is Getting Faster, Thanks to AI appeared first on SD Times.

## Synthetic identities leave US lenders with $2.4 billion in fraud exposure

DevFeed: [Synthetic identities leave US lenders with $2.4 billion in fraud exposure](<https://devfeed.tech/articles/synthetic-identities-leave-us-lenders-with-2-4-billion-in-fraud-exposure-99702.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/10/26/transunion-synthetic-identity-fraud-risks-report/>)

Author: Anamarija Pogorelec

Published: 2026-10-26T05:00:59Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [fake account fraud](<https://devfeed.tech/topics/fake-account-fraud.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [account takeover](<https://devfeed.tech/topics/account-takeover.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Credential theft](<https://devfeed.tech/topics/credential-theft.md>), [pii](<https://devfeed.tech/topics/pii.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [account](<https://devfeed.tech/tags/account.md>), [ai](<https://devfeed.tech/tags/ai.md>), [attack](<https://devfeed.tech/tags/attack.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [digital](<https://devfeed.tech/tags/digital.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-industry](<https://devfeed.tech/tags/financial-industry.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [identity](<https://devfeed.tech/tags/identity.md>), [identity-protection](<https://devfeed.tech/tags/identity-protection.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [manipulate](<https://devfeed.tech/tags/manipulate.md>), [money](<https://devfeed.tech/tags/money.md>), [network](<https://devfeed.tech/tags/network.md>), [news](<https://devfeed.tech/tags/news.md>), [personal](<https://devfeed.tech/tags/personal.md>), [report](<https://devfeed.tech/tags/report.md>), [risks](<https://devfeed.tech/tags/risks.md>), [scams](<https://devfeed.tech/tags/scams.md>), [security](<https://devfeed.tech/tags/security.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [transactions](<https://devfeed.tech/tags/transactions.md>), [transunion](<https://devfeed.tech/tags/transunion.md>), [trust](<https://devfeed.tech/tags/trust.md>), [us](<https://devfeed.tech/tags/us.md>)

### AI overview

TransUnion reports that 81% of suspected digital fraud in its network in the first half of 2026 occurred during logins or financial transactions, showing that identity checks at onboarding do not protect the full customer relationship. The excerpt describes impersonation scams that persuade customers to share codes, reset credentials or redirect payments, and synthetic identities built from exposed personal data and AI that can pass verification and be reused across services. US lenders had an estimated $2.4 billion in synthetic identity fraud risk exposure at the end of June 2026, including $1.5 billion in auto lending; these figures are potential losses, not losses already incurred. The report also notes attackers target account recovery and secondary authentication, while fraud patterns vary by region.

### Source excerpt

Criminals are exploiting established customer accounts and familiar brands to steal money and personal information, according to TransUnion's Fraud in the Age of Continuous Trust report. Eighty-one percent of suspected digital fraud in its network during the first half of 2026 occurred during account logins and financial transactions, highlighting risks that persist throughout a customer relationship. Verifying someone's identity does not establish whether every subsequent interaction can be trusted. Scammers can manipulate legitimate customers into ... More -> The post Synthetic identities leave US lenders with $2.4 billion in fraud exposure appeared first on Help Net Security.

## Broadcom adds real-time scam detection to 3-D Secure authentication

DevFeed: [Broadcom adds real-time scam detection to 3-D Secure authentication](<https://devfeed.tech/articles/broadcom-adds-real-time-scam-detection-to-3-d-secure-authentication-95349.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/10/22/broadcom-arcot-scam-defense/>)

Author: Industry News

Published: 2026-10-22T11:18:09Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [MFA](<https://devfeed.tech/topics/mfa.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [broadcom](<https://devfeed.tech/tags/broadcom.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [industry-news](<https://devfeed.tech/tags/industry-news.md>), [payment](<https://devfeed.tech/tags/payment.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [scam-detection](<https://devfeed.tech/tags/scam-detection.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>)

### AI overview

Arcot Scam Defense adds a real-time risk layer to Arcot by Broadcom's 3-D Secure flow, designed to catch social engineering even after a cardholder passes an OTP or biometric challenge. It combines transaction, device, historical-behavior and challenge-interaction signals, such as delayed OTP entry or location differences between checkout and authentication devices, rather than relying on one indicator. It can also integrate with third-party services to detect whether the authenticating device is on a phone call. In one issuer pilot using a month of live data, reviewing the top 1% of successful challenges was estimated to protect $4 million in fraud, with a 0.38-point reduction in authentication success rate. Broadcom says it plans to add cardholder and device attributes and challenge-history profiling.

### Source excerpt

Broadcom has announced the launch of Arcot Scam Defense, a new feature of Arcot by Broadcom, designed to block social engineering fraud during card-not-present (CNP) transactions. "Financial institutions are experiencing broad increases in fraud attempts driven by sophisticated, AI-enhanced social engineering attacks," said Matt Cooke, VP and GM, Payment Security Division, Broadcom. "While technological security systems have advanced and are highly effective at blocking fraud, fraudsters have pivoted their efforts to hacking customers directly. By ... More -> The post Broadcom adds real-time scam detection to 3-D Secure authentication appeared first on Help Net Security.

## Leading European Financial Services Organizations Embrace Open Models to Build Proprietary Intelligence

DevFeed: [Leading European Financial Services Organizations Embrace Open Models to Build Proprietary Intelligence](<https://devfeed.tech/articles/leading-european-financial-services-organizations-embrace-open-models-to-build-proprietary-intelligence-95045.md>)

Original publisher: [Read original article](<https://blogs.nvidia.com/blog/european-financial-services-organizations-open-models-proprietary-intelligence/>)

Author: Jason Renders

Published: 2026-10-22T05:00:56Z

Content type: news

Language: en

Sources: [NVIDIA](<https://devfeed.tech/sources/nvidia-blog.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [digital sovereignty](<https://devfeed.tech/topics/digital-sovereignty.md>), [RAPIDS](<https://devfeed.tech/topics/rapids.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Dynamo-Triton](<https://devfeed.tech/topics/dynamo-triton.md>)

Tags: [accelerated-computing](<https://devfeed.tech/tags/accelerated-computing.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [banking](<https://devfeed.tech/tags/banking.md>), [banks](<https://devfeed.tech/tags/banks.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [blackwell-ultra](<https://devfeed.tech/tags/blackwell-ultra.md>), [civo](<https://devfeed.tech/tags/civo.md>), [cudf](<https://devfeed.tech/tags/cudf.md>), [data-pipelines](<https://devfeed.tech/tags/data-pipelines.md>), [detection](<https://devfeed.tech/tags/detection.md>), [dynamo-triton](<https://devfeed.tech/tags/dynamo-triton.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [gtc-2026](<https://devfeed.tech/tags/gtc-2026.md>), [nvidia-blackwell](<https://devfeed.tech/tags/nvidia-blackwell.md>), [open](<https://devfeed.tech/tags/open.md>), [open-weight-models](<https://devfeed.tech/tags/open-weight-models.md>), [revolut](<https://devfeed.tech/tags/revolut.md>)

### AI overview

The excerpt presents European financial organizations using open or specialized models and accelerated computing on their own or sovereign infrastructure to build financial intelligence. Revolut is scaling its PRAGMA foundation model with NVIDIA cuDF and Dynamo-Triton on Blackwell Ultra GPUs for an initial 80 million customers, with engineering for 3x scale. Starling trained Starling Intelligence on its transaction data in U.K. sovereign cloud; Lloyds built ATUM from banking transactions using RTX PRO 6000 Blackwell GPUs; SBS offers a platform for models that keep data within banks. Other examples include bunq's Finn, reported to match leading closed-model quality at 60% of the cost per answer on Nebius, and Santander's use of NVIDIA Kumo models for structured financial data. For research, LSEG reports up to 10x faster historical tick-data analysis with Polars GPU and cuDF. For fraud pipelines, HSBC cites 5x faster data processing, while Stripe reports 42x faster pipelines and 92% cost savings in offline testing with GPU-accelerated Ray Data.

### Source excerpt

At GTC Berlin, banks, payment companies and financial data providers are showing what production-scale intelligence looks like -- built on NVIDIA accelerated computing, powered by open weight models and running on their own infrastructure. Revolut is rebuilding its technology stack on a single foundation model PRAGMA, powered by NVIDIA accelerated computing. Using the NVIDIA cuDF [...]

## Trends from Money20/20 2026: The rise of "hidden" financial services

DevFeed: [Trends from Money20/20 2026: The rise of "hidden" financial services](<https://devfeed.tech/articles/trends-from-money20-20-2026-the-rise-of-hidden-financial-services-96039.md>)

Original publisher: [Read original article](<https://stripe.com/blog/trends-from-money20-20-2026-the-rise-of-hidden-financial-services>)

Author: Fergal Madigan

Published: 2026-10-22T00:00:00Z

Content type: news

Language: en

Sources: [Stripe](<https://devfeed.tech/sources/stripe-blog.md>)

Topics: [Finance](<https://devfeed.tech/topics/finance.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [stripe](<https://devfeed.tech/topics/stripe.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-commerce](<https://devfeed.tech/tags/agentic-commerce.md>), [agentic-payments](<https://devfeed.tech/tags/agentic-payments.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [american-express](<https://devfeed.tech/tags/american-express.md>), [app](<https://devfeed.tech/tags/app.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [fintech](<https://devfeed.tech/tags/fintech.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [money](<https://devfeed.tech/tags/money.md>), [products](<https://devfeed.tech/tags/products.md>), [stablecoins](<https://devfeed.tech/tags/stablecoins.md>), [trends](<https://devfeed.tech/tags/trends.md>)

### AI overview

Money20/20 speakers described financial infrastructure becoming less visible as stablecoins, always-on settlement, and AI agents enable new services. Businesses can embed white-labeled stablecoin wallets in familiar apps, potentially reaching users without requiring a separate crypto product. Round-the-clock money movement can reduce advance forecasting and prefunding: Citi described using tokenized deposits to fund US equity purchases during a Singapore holiday, while stablecoin-based lending and earnings products serve demand outside banking hours. Agentic payments require machine-readable instructions defining permitted purchases, amounts, sellers, purposes, and expiration. Stripe described spend requests that buyers can approve before completion; American Express discussed receiving purchase instructions earlier to set controls. The article notes that longer-running permissions may need to remain adjustable and revocable.

### Source excerpt

As fintech products become increasingly capable, the infrastructure behind them fades into the background. Three trends from Money20/20 show how stablecoins, agents, and always-on money are changing financial services.

[Next page](<https://devfeed.tech/topics/payment-fraud.md?cursor=WyIyMDI2LTEwLTIyVDAwOjAwOjAwKzAwOjAwIiwgIjRkMDJhMjQzLWE4ZjQtNDdjMS1hNGYwLWRlMjAwMWVjMGMxYSJd>)