# face recognition

Published articles for face recognition.

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

## A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks

DevFeed: [A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks](<https://devfeed.tech/articles/a-bag-of-tricks-for-defending-deep-learning-based-face-recognition-pipelines-against-backdoor-attacks-118464.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06412>)

Author: Quentin Le Roux, Marti Jimenez, Yannick Teglia, Philippe Loubet Moundi

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>)

Tags: [backdoor](<https://devfeed.tech/tags/backdoor.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [defense](<https://devfeed.tech/tags/defense.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [hardening](<https://devfeed.tech/tags/hardening.md>), [inference](<https://devfeed.tech/tags/inference.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>)

### AI overview

The report addresses backdoor attacks caused by poisoned training data from potentially compromised third parties, even when face recognition models are trained in-house. It presents three practical defenses for multi-stage face recognition systems: one detects poisoned identities during training or before deployment, while two filter suspicious inputs at inference time before a response reaches a potential attacker. The abstract says the methods' motivations, algorithms, and computational impact are evaluated on realistic face recognition workloads, but does not identify the techniques or report results.

### Source excerpt

arXiv:2611.06412v1 Announce Type: cross Abstract: The protection of mature, multi-stage Face Recognition Systems is crucial to system providers. This technical report targets the threat model most relevant to industry practitioners: although model training is performed in-house, training data is sourced from possibly-compromised third parties. Given this setting, we present three practical defense "tricks" against data poisoning-based backdoor attacks. The first operates at training-time, detecting poisoned identities during training or prior to a pipeline's deployment. The last two operate at inference-time, filtering suspicious inputs before an answer can be sent back to a potential attacker. Each method is presented with their motivation, algorithms and computational impact, and evaluated on realistic face recognition workloads. Our goal is to provide actionable hardening techniques to system providers.

## AEGIS: Preserving Privacy of 3D Facial Avatars with Adversarial Perturbations

DevFeed: [AEGIS: Preserving Privacy of 3D Facial Avatars with Adversarial Perturbations](<https://devfeed.tech/articles/aegis-preserving-privacy-of-3d-facial-avatars-with-adversarial-perturbations-118184.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2511.17747>)

Author: Dawid Wolkiewicz, Anastasiya Pechko, Przemys{\\l}aw Spurek, Piotr Syga

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

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

Topics: [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [3D](<https://devfeed.tech/topics/3d.md>), [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [animation](<https://devfeed.tech/tags/animation.md>), [avatar](<https://devfeed.tech/tags/avatar.md>), [biometric-authentication](<https://devfeed.tech/tags/biometric-authentication.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [identity-protection](<https://devfeed.tech/tags/identity-protection.md>), [identity-theft](<https://devfeed.tech/tags/identity-theft.md>), [masking](<https://devfeed.tech/tags/masking.md>), [metric](<https://devfeed.tech/tags/metric.md>), [networks](<https://devfeed.tech/tags/networks.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

AEGIS protects the identity of 3D Gaussian facial avatars by perturbing the primitives' base color coefficients, guided by an ensemble of pretrained face verification networks. Because the protection is embedded in the 3D representation, it applies across viewpoints and animations without retraining or changing avatar geometry. In evaluations against black-box recognizers, the method reduced face retrieval and verification accuracy to near zero while maintaining perceptual fidelity and preserving age, gender, and emotion. The authors also introduce a viewpoint-robust leakage metric to measure residual identity exposure across rendered views.

### Source excerpt

arXiv:2511.17747v2 Announce Type: replace-cross Abstract: The growing adoption of photorealistic 3D facial avatars, particularly those utilizing efficient 3D Gaussian Splatting representations, introduces new risks of online identity theft, especially in systems that rely on biometric authentication. While effective adversarial masking methods have been developed for 2D images, a significant gap remains in achieving robust, viewpoint-consistent identity protection for dynamic 3D avatars. To address this, we present AEGIS, the first privacy-preserving identity masking framework for 3D Gaussian avatars, concealing identity from automated face recognition while preserving the avatar's perceptual realism and animation usability. AEGIS applies adversarial perturbations to the base (DC) color coefficients of the Gaussian primitives, guided by an ensemble of pre-trained face verification networks, embedding the protection directly in the 3D representation so that it applies across viewpoints and animations, without retraining or modifying the avatar's geometry. Evaluated against black-box recognizers, AEGIS reduces face retrieval and verification accuracy to near-zero while maintaining high perceptual fidelity. It also preserves key facial attributes such as age, gender, and emotion, demonstrating strong privacy protection with minimal visual distortion. We further introduce a viewpoint-robust leakage metric that quantifies residual identity leakage across an avatar's rendered viewpoints, which single-view evaluation cannot capture.

## Developing a Dynamic Multi-factor Authentication System for Securing Smart Organizations

DevFeed: [Developing a Dynamic Multi-factor Authentication System for Securing Smart Organizations](<https://devfeed.tech/articles/developing-a-dynamic-multi-factor-authentication-system-for-securing-smart-organizations-103370.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36926>)

Author: Mohsen Saffar, Hamid Reza Naji

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [MFA](<https://devfeed.tech/topics/mfa.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>)

Tags: [aes](<https://devfeed.tech/tags/aes.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [big-data](<https://devfeed.tech/tags/big-data.md>), [biometric-authentication](<https://devfeed.tech/tags/biometric-authentication.md>), [continuous-verification](<https://devfeed.tech/tags/continuous-verification.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [encryption](<https://devfeed.tech/tags/encryption.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [fingerprint](<https://devfeed.tech/tags/fingerprint.md>), [iot](<https://devfeed.tech/tags/iot.md>), [markov](<https://devfeed.tech/tags/markov.md>), [markov-chain](<https://devfeed.tech/tags/markov-chain.md>), [mfa](<https://devfeed.tech/tags/mfa.md>), [multi-factor-authentication](<https://devfeed.tech/tags/multi-factor-authentication.md>), [multi-factor-authentication-mfa](<https://devfeed.tech/tags/multi-factor-authentication-mfa.md>), [performance-analysis](<https://devfeed.tech/tags/performance-analysis.md>)

### AI overview

The proposed system combines continuous verification under Zero Trust Architecture with Markov-chain selection of fingerprint, iris, or face authentication factors, aiming to make biometric checks less predictable. It uses CASIA biometric datasets and AES-128 encryption to manage authentication and user data. The abstract reports that performance analysis found a balance between security and efficiency, and presents the approach as suited to smart organizations, particularly e-government. No specific performance measurements or comparative results are provided in the supplied text.

### Source excerpt

arXiv:2610.36926v1 Announce Type: new Abstract: As smart organizations increasingly rely on technologies like AI, big data, and IoT, securing these systems is crucial. This research introduces a dynamic multi-factor authentication (MFA) system within the Zero Trust Architecture (ZTA) framework, which enforces continuous verification. The system randomly selects biometric authentication factors, such as fingerprint, iris, and face recognition using a Markov chain model to ensure adaptability and reduce predictability in security measures. Using CASIA biometric datasets and AES-128 encryption, the system securely manages user data and authentication. Performance analysis shows that the dynamic selection process balances security and efficiency, making it suitable for smart organizations, particularly in e-government contexts. This MFA system strengthens cybersecurity by providing a flexible, real-time defense against evolving threats.

## Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching

DevFeed: [Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching](<https://devfeed.tech/articles/steering-the-flow-inverting-face-recognition-models-via-gradient-guided-flow-matching-101355.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.16791>)

Author: Ye Lu, Shen Wang, Zhaoyang Zhang, Yihan Yan, Li Liu, Runze Liu, Fanghui Sun

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [identity](<https://devfeed.tech/tags/identity.md>), [security](<https://devfeed.tech/tags/security.md>), [steering](<https://devfeed.tech/tags/steering.md>), [white-box](<https://devfeed.tech/tags/white-box.md>)

### AI overview

SFMI reconstructs representative target-identity faces through a two-stage white-box attack: it first trains an unconditional Flow Matching model as a face prior, then uses a Progressive Guidance Scheduler to inject time-dependent, target-specific gradients from intermediate generated states into the sampling vector field. The method is intended to steer generation from random noise toward high-density regions of the target class. In an identity-disjoint CelebA cross-evaluation, it reports ACC 0.9248, FID 22.61, and LPIPS 0.3874 against ArcFace; the abstract describes results across multiple target models as competitive in attack success and visual fidelity under the evaluated white-box protocol.

### Source excerpt

arXiv:2608.16791v2 Announce Type: replace-cross Abstract: Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images. In this paper, we propose Steering Flow Model Inversion (SFMI), a novel two-stage white-box model inversion method that reformulates inversion as a trajectory-steering task. Specifically, Step I, Learning a Generic Flow Matching Prior, pre-trains a generic unconditional Flow Matching model to encode the manifold of human faces as a robust prior. Step II, Attacking with Progressive Guidance Scheduler (PGS), injects time-dependent target-specific gradients during sampling. By backpropagating through the target model to obtain gradients from intermediate generated states, PGS progressively injects adaptive guidance signals into the vector field. This process effectively steers the current generative flow from random noise toward the high-density regions of the target class. Under an identity-disjoint cross-evaluation setting using the CelebA dataset, SFMI achieves an ACC of 0.9248, an FID of 22.61, and an LPIPS of 0.3874 on the ArcFace target. Extensive experiments on multiple target models demonstrate that SFMI achieves competitive state-of-the-art performance in attack success and visual fidelity under the evaluated white-box protocol.

## GhostFaceMPC: Privacy-Preserving Face Recognition with Multi-Party Computation

DevFeed: [GhostFaceMPC: Privacy-Preserving Face Recognition with Multi-Party Computation](<https://devfeed.tech/articles/ghostfacempc-privacy-preserving-face-recognition-with-multi-party-computation-94546.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.29987>)

Author: Davide Carnemolla, Dario Catalano, Mario Di Raimondo

Published: 2026-10-22T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [circuit](<https://devfeed.tech/tags/circuit.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [facial-recognition](<https://devfeed.tech/tags/facial-recognition.md>), [matching](<https://devfeed.tech/tags/matching.md>), [network](<https://devfeed.tech/tags/network.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

GhostFaceMPC applies secure multi-party computation to face recognition, covering feature extraction, storage and matching without exposing raw images or biometric embeddings at any stage. The paper describes a quantization of GhostFaceNet designed for MPC and circuit optimizations intended to make this processing practical. The supplied excerpt does not report performance measurements or implementation requirements.

### Source excerpt

arXiv:2610.29987v1 Announce Type: new Abstract: Facial recognition has become central to modern authentication systems, security frameworks, and personalized services. However, its widespread adoption is hindered by severe privacy risks, particularly surrounding unauthorized access to sensitive biometric data. To address these challenges, this paper presents GhostFaceMPC, the first end-to-end, privacy-preserving face recognition system to evaluate a deep convolutional neural network extractor and matching under secure multi-party computation. GhostFaceMPC enables secure processing of facial data across all stages of a face recognition process, from feature extraction and storage to matching, without exposing raw images or biometric embeddings at any stage. We introduce a multi-party computation-friendly quantization of the GhostFaceNet model and circuit optimizations that make face recognition under multi-party computation practical. The code is available at https://github.com/crypto-unict/GhostFaceMPC.

## XIMEA MU003TG-SY-UC - A miniature, modular 0.3MP USB 3.0 ToF Sensor based on Sony IMX556

DevFeed: [XIMEA MU003TG-SY-UC - A miniature, modular 0.3MP USB 3.0 ToF Sensor based on Sony IMX556](<https://devfeed.tech/articles/ximea-mu003tg-sy-uc-a-miniature-modular-0-3mp-usb-3-0-tof-sensor-based-on-sony-imx556-65308.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/10/06/ximea-mu003tg-sy-uc-a-miniature-modular-0-3mp-usb-3-0-tof-sensor-based-on-sony-imx556/>)

Author: Debashis Das

Published: 2026-10-06T09:00:22Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Embedded Software Dev](<https://devfeed.tech/topics/embedded-software-dev.md>), [User Interfaces](<https://devfeed.tech/topics/user-interfaces.md>), [Network](<https://devfeed.tech/topics/network.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [camera](<https://devfeed.tech/tags/camera.md>), [cmos](<https://devfeed.tech/tags/cmos.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [embedded-systems](<https://devfeed.tech/tags/embedded-systems.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [machine-vision](<https://devfeed.tech/tags/machine-vision.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [sensors](<https://devfeed.tech/tags/sensors.md>), [sony](<https://devfeed.tech/tags/sony.md>), [usb](<https://devfeed.tech/tags/usb.md>)

### AI overview

The XIMEA MU003TG-SY-UC is a compact industrial ToF camera built around a 0.3MP Sony IMX556 sensor. It connects over USB 3.2 Gen 1 and provides phase data for host-side depth calculation; a separate VCSEL illumination board and related components are required for depth sensing. The article also describes the camera's dimensions, acquisition modes, software support, and Engineering Sample status.

### Source excerpt

The XIMEA MU003TG-SY-UC is a miniature industrial Time-of-Flight (ToF) camera with a 0.3MP Sony IMX556 CMOS sensor, global shutter, 640 x 480 resolution, and a 60 FPS frame rate. Its compact 26.4 x 26.4 x 28.67 mm enclosure and 31-gram weight make it suitable for space-limited embedded vision systems, robotics, UAVs, kiosks, 3D scanning, face recognition, and other machine-vision applications. The module uses a USB 3.2 Gen 1 interface through a 14-pin I-PEX Cabline SS connector for data, power, and control. A separate 10-pin Cabline V connector provides synchronization with external VCSEL illumination. The camera does not include an illumination source or optical band-pass filter, so these components must be provided separately for depth sensing. XIMEA MU003TG-SY-UC specifications: Sensor - Sony IMX556 CMOS Time-of-Flight sensor, global shutter, no on-sensor filter Resolution - 0.3 megapixels (640 x 480); active area 6.4 x 4.8 mm Pixel Size - 10 µm x 10 [...] The post XIMEA MU003TG-SY-UC - A miniature, modular 0.3MP USB 3.0 ToF Sensor based on Sony IMX556 appeared first on CNX Software - Embedded Systems News.

## Quiz: Build Your Own Face Recognition Tool With Python

DevFeed: [Quiz: Build Your Own Face Recognition Tool With Python](<https://devfeed.tech/articles/quiz-build-your-own-face-recognition-tool-with-python-4404.md>)

Original publisher: [Read original article](<https://realpython.com/quizzes/face-recognition-with-python/>)

Author: Real Python

Published: 2026-09-05T12:00:00Z

Content type: tutorial

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [Python](<https://devfeed.tech/topics/python.md>)

Tags: [command-line](<https://devfeed.tech/tags/command-line.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [python](<https://devfeed.tech/tags/python.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

An interactive 10-question quiz that tests understanding of a Python face recognition tool, including face detection versus recognition, face encodings, voting-based matching, model validation, bounding box coordinates, and argparse command-line options.

### Source excerpt

Check your understanding of face detection, face recognition, face encodings, bounding boxes, and model validation in Python.

## EFF and Civil Society Groups Call on Nottinghamshire Police to Halt Live Face Recognition

DevFeed: [EFF and Civil Society Groups Call on Nottinghamshire Police to Halt Live Face Recognition](<https://devfeed.tech/articles/eff-and-civil-society-groups-call-on-nottinghamshire-police-to-halt-live-face-recognition-50637.md>)

Original publisher: [Read original article](<https://www.eff.org/deeplinks/2026/08/eff-and-civil-society-groups-call-nottinghamshire-police-halt-live-face>)

Author: Paige Collings

Published: 2026-08-21T16:03:17Z

Content type: opinion

Language: en

Sources: [Deeplinks](<https://devfeed.tech/sources/deeplinks.md>)

Topics: [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>), [Risk](<https://devfeed.tech/topics/risk.md>)

Tags: [camera](<https://devfeed.tech/tags/camera.md>), [children](<https://devfeed.tech/tags/children.md>), [crime](<https://devfeed.tech/tags/crime.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [face-surveillance](<https://devfeed.tech/tags/face-surveillance.md>), [surveillance](<https://devfeed.tech/tags/surveillance.md>), [surveillance-technologies](<https://devfeed.tech/tags/surveillance-technologies.md>), [uk](<https://devfeed.tech/tags/uk.md>)

### AI overview

EFF and civil society organizations urge Nottinghamshire Police to halt a proposed rollout of live facial recognition, citing mass surveillance, disproportionate targeting of children, social risks, and insufficient public support.

### Source excerpt

This week, EFF, along with Big Brother Watch, Defend Digital Me, Liberty, Open Rights Group, Race Equality First, Statewatch, and Stopwatch, wrote to Nottinghamshire Police Force in the UK raising concern about the proposed roll-out of live facial recognition technology (LFR), and called for its immediate halt. In particular, the letter highlights six concerns: LFR Is Not "Just Another Tool" Nottinghamshire Police has stated that "facial recognition is just another tool to fight crime." But LFR used in public spaces is an incredibly intrusive biometric mass surveillance technology that scans the faces of everyone who walks past the camera and takes biometric face prints. This is not just another tool, but a major escalation of surveillance that treats everyone as a suspect by default. People Having "Nothing to Worry About" Does Not Hold to Scrutiny According to Nottinghamshire Police, "if you aren't entering the city or county to commit crime then you have nothing to worry about." However, many people have legitimate concerns about the normalisation of invasive technologies. So a public that cannot move around their towns and cities without being subjected to a biometric identity check may be less willing to seek medical care or legal advice, speak with journalists, act in a union, vote, protest, or express their gender, sexual or religious identity. Disproportionate Targeting With LFR We are particularly concerned to learn that Nottinghamshire Police could deploy LFR to tackle low level crimes, such as youth behavior deemed anti-social, as part of Operation View. Reporting suggests that the force already possesses "a watchlist of young people believed to be causing the most problems," including children as young as 11 years old. It would be highly disproportionate to deploy live facial recognition to tackle this behaviour. Many of these children are reportedly known to the police, and it is highly likely that there are more proportionate means for locating them. LF

## Building for XREAL AURA: Inside Google's First Android XR Hackathon

DevFeed: [Building for XREAL AURA: Inside Google's First Android XR Hackathon](<https://devfeed.tech/articles/building-for-xreal-aura-inside-google-s-first-android-xr-hackathon-79574.md>)

Original publisher: [Read original article](<https://unity.com/blog/inside-google-s-first-xr-hackathon>)

Author: Leah Martin

Published: 2026-07-01T00:00:00Z

Content type: article

Language: en

Sources: [Unity](<https://devfeed.tech/sources/unity.md>)

Topics: [Android XR](<https://devfeed.tech/topics/android-xr.md>), [Unity](<https://devfeed.tech/topics/unity.md>), [Hackathon](<https://devfeed.tech/topics/hackathon.md>), [Jetpack Compose](<https://devfeed.tech/topics/jetpack-compose.md>), [Google Cloud Platform (GCP)](<https://devfeed.tech/topics/google-cloud.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android-xr](<https://devfeed.tech/tags/android-xr.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [hackathon](<https://devfeed.tech/tags/hackathon.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [unity](<https://devfeed.tech/tags/unity.md>)

### AI overview

At Google's first Android XR hackathon, 19 teams built for XREAL AURA in two days. Four of the five finalists used Unity. The article describes why teams chose Unity or other development approaches, highlights healthcare and robotics projects, and names the winning entries.

### Source excerpt

At Google's first Android XR hackathon 19 teams built for XREAL AURA in two days, and four of five finalists chose Unity. See who won and why.

## ESP-WHO: Get started

DevFeed: [ESP-WHO: Get started](<https://devfeed.tech/articles/esp-who-get-started-13770.md>)

Original publisher: [Read original article](<https://developer.espressif.com/blog/2026/05/esp-who-get-started/>)

Author: John Lee

Published: 2026-05-28T00:00:00Z

Content type: tutorial

Language: en

Sources: [Blog on Developer Portal](<https://devfeed.tech/sources/blog-on-developer-portal.md>)

Topics: [Tutorial](<https://devfeed.tech/topics/tutorial.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [ESP32-S3](<https://devfeed.tech/topics/esp32-s3.md>), [ESP-IDF](<https://devfeed.tech/topics/esp-idf.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Framework](<https://devfeed.tech/topics/framework.md>), [software-development](<https://devfeed.tech/topics/software-development.md>)

Tags: [blog](<https://devfeed.tech/tags/blog.md>), [camera](<https://devfeed.tech/tags/camera.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [dl](<https://devfeed.tech/tags/dl.md>), [esp-idf](<https://devfeed.tech/tags/esp-idf.md>), [esp-who](<https://devfeed.tech/tags/esp-who.md>), [esp32](<https://devfeed.tech/tags/esp32.md>), [esp32-s3](<https://devfeed.tech/tags/esp32-s3.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [image-processing](<https://devfeed.tech/tags/image-processing.md>), [inference](<https://devfeed.tech/tags/inference.md>), [led](<https://devfeed.tech/tags/led.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

This tutorial explains how to set up ESP-WHO on the ESP32-S3-EYE board, run a face recognition example, and extend it with custom detection callbacks. It covers the platform architecture, component pipeline, hardware abstraction, prerequisites, and an LED response when a face is detected.

### Source excerpt

In this article, we will set up ESP-WHO on the ESP32-S3-EYE board, running a face recognition example, and extending it with custom detection callbacks.

## Frigate 0.17.1 Release

DevFeed: [Frigate 0.17.1 Release](<https://devfeed.tech/articles/0-17-1-release-89423.md>)

Original publisher: [Read original article](<https://github.com/blakeblackshear/frigate/releases/tag/v0.17.1>)

Author: blakeblackshear

Published: 2026-03-22T20:33:17Z

Content type: release

Language: en

Sources: [Release notes from frigate](<https://devfeed.tech/sources/release-notes-from-frigate.md>)

Topics: [Release notes](<https://devfeed.tech/topics/release-notes.md>), [project release](<https://devfeed.tech/topics/project-release.md>)

Tags: [admin](<https://devfeed.tech/tags/admin.md>), [auth](<https://devfeed.tech/tags/auth.md>), [avx2](<https://devfeed.tech/tags/avx2.md>), [bugfixes](<https://devfeed.tech/tags/bugfixes.md>), [config](<https://devfeed.tech/tags/config.md>), [details](<https://devfeed.tech/tags/details.md>), [docs](<https://devfeed.tech/tags/docs.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [genai](<https://devfeed.tech/tags/genai.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [models](<https://devfeed.tech/tags/models.md>), [mqtt](<https://devfeed.tech/tags/mqtt.md>), [onnx](<https://devfeed.tech/tags/onnx.md>), [playback](<https://devfeed.tech/tags/playback.md>), [release](<https://devfeed.tech/tags/release.md>), [security-fixes](<https://devfeed.tech/tags/security-fixes.md>), [snapshots](<https://devfeed.tech/tags/snapshots.md>), [storage](<https://devfeed.tech/tags/storage.md>), [stream](<https://devfeed.tech/tags/stream.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

Frigate 0.17.1 is a maintenance release with security fixes and targeted bug corrections. It restricts the raw configuration endpoint to admins and fixes cross-camera authorization in timeline and media endpoints. Other notable fixes address RKNN ArcFace input formatting and prevent storage cleanup from running in safe mode. The change list also includes fixes for go2rtc authentication and configuration, graceful handling of missing previews, thumbnail encoding, role-based filtering of push notifications, and tracking-detail video playback. The notes list container images for standard, ARM64, TensorRT, RKNN, ROCm, Jetson 6 TensorRT, and Synaptics builds.

### Source excerpt

This is a maintenance release for Frigate 0.17 that includes bugfixes and minor changes. Images ghcr.io/blakeblackshear/frigate:0.17.1 ghcr.io/blakeblackshear/frigate:0.17.1-standard-arm64 ghcr.io/blakeblackshear/frigate:0.17.1-tensorrt ghcr.io/blakeblackshear/frigate:0.17.1-rk ghcr.io/blakeblackshear/frigate:0.17.1-rocm ghcr.io/blakeblackshear/frigate:0.17.1-tensorrt-jp6 ghcr.io/blakeblackshear/frigate:0.17.1-synaptics What's Changed Security Fixes Restrict raw config endpoint to admin role by @hawkeye217 in #22523 Fix cross-camera auth in timeline and media endpoints by @hawkeye217 in #22522 Notable Changes Fix/rknn arcface input format master by @begetan in #22319 Don't try to run storage cleanup if frigate is in safe mode by @hawkeye217 in #22492 Other Changes docs: fix image address by @ZhaiSoul in #22067 docs: fix hailo setup numbering error by @ZhaiSoul in #22066 Fix script for downloading RF-DETR by @f0ff886f in #22083 docs: Add frame selection and clean copy details to snapshots docs by @webmasterkai in #21946 Update line breaks in video_pipeline.md diagram by @GrumpyMeow in #21919 docs: Add detail to face recognition MQTT update docs by @webmasterkai in #21942 Update HA docs with MQTT example by @hawkeye217 in #22098 Docs: fix YOLOv9 onnx export by @tremby in #22107 Docs updates by @hawkeye217 in #22131 updates for yolov9 coral support by @blakeblackshear in #22136 0.17 Release by @blakeblackshear in #19787 Fix link to Coral YOLOv9 Frigate+ models by @hawkeye217 in #22164 Fix go2rtc stream alias auth by @hawkeye217 in #22097 Birdseye fixes by @hawkeye217 in #22166 Fix genai by @NickM-27 in #22203 Docs updates by @hawkeye217 in #22222 Fix menu display conditions by @hawkeye217 in #22237 docs: updated the guides detectors section by @ZhaiSoul in #22241 Docs update by @hawkeye217 in #22251 Update docs for new HA language by @hawkeye217 in #22258 Update docs for AVX2 CPU requirement by @hawkeye217 in #22305 Improve playback of videos in Tracking Details by @ha

## ESP-SparkBot：Large Language Model Robot with ESP32-S3

DevFeed: [ESP-SparkBot：Large Language Model Robot with ESP32-S3](<https://devfeed.tech/articles/esp-sparkbot-large-language-model-robot-with-esp32-s3-13694.md>)

Original publisher: [Read original article](<https://developer.espressif.com/blog/2025/04/esp32-s3-sparkbot/>)

Author: John Lee

Published: 2025-04-23T00:00:00Z

Content type: article

Language: en

Sources: [Blog on Developer Portal](<https://devfeed.tech/sources/blog-on-developer-portal.md>)

Topics: [ESP32-S3](<https://devfeed.tech/topics/esp32-s3.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [software-development](<https://devfeed.tech/topics/software-development.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [blog](<https://devfeed.tech/tags/blog.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [esp-now](<https://devfeed.tech/tags/esp-now.md>), [esp32-s3](<https://devfeed.tech/tags/esp32-s3.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [facial-recognition](<https://devfeed.tech/tags/facial-recognition.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [home-automation](<https://devfeed.tech/tags/home-automation.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [motion-detection](<https://devfeed.tech/tags/motion-detection.md>), [offline-speech-recognition](<https://devfeed.tech/tags/offline-speech-recognition.md>), [usb-screen-mirror](<https://devfeed.tech/tags/usb-screen-mirror.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

This article introduces ESP-SparkBot, a low-cost, multifunctional AI robot built with ESP32-S3. It describes the robot's voice interaction, facial recognition, remote control, motion detection, multimedia capabilities, hardware design, power options, and supporting software framework.

### Source excerpt

This article provides an overview of the ESP-SparkBot, its features, and functionality.It also details the hardware design and outlines the software framework that supports its operation. Introduction# With the booming development of generative artificial intelligence, large language models (LLMs) are becoming a core technology in the AI field.

## Building Intelligent Apps with Apple AI Models

DevFeed: [Building Intelligent Apps with Apple AI Models](<https://devfeed.tech/articles/building-intelligent-apps-with-apple-ai-models-11523.md>)

Original publisher: [Read original article](<https://www.kodeco.com/ios/paths/apple-ai-models>)

Published: 2024-09-18T00:00:00Z

Content type: tutorial

Language: en

Sources: [Kodeco](<https://devfeed.tech/sources/kodeco-high-quality-programming-tutorials-ios-android-swift-kotlin-unity-and-more.md>)

Topics: [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [object-detection](<https://devfeed.tech/topics/object-detection.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [App](<https://devfeed.tech/topics/app.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [app](<https://devfeed.tech/tags/app.md>), [apple](<https://devfeed.tech/tags/apple.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [course](<https://devfeed.tech/tags/course.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [framework](<https://devfeed.tech/tags/framework.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [object-detection](<https://devfeed.tech/tags/object-detection.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>)

### AI overview

A learning path about building intelligent apps with Apple AI Models. It covers on-device machine learning, computer vision with the Vision framework, real-time translation with the Translation framework, and customizing pre-built models with Create ML.

### Source excerpt

This course explores on-device machine learning using Apple's powerful tools. See how simple the Vision framework makes complex computer vision tasks, enabling your app to understand the real world, through tasks like object detection and face recognition. Learn to leverage the Translation framework for on-device, real-time language translation, breaking down language barriers for your users. Before finally looking at how to develop your own machine learning models, by customizing Apple's pre-built models for specific use cases within your apps.

## Hacking FaceNet using Adversarial examples

DevFeed: [Hacking FaceNet using Adversarial examples](<https://devfeed.tech/articles/hacking-facenet-using-adversarial-examples-21534.md>)

Original publisher: [Read original article](<http://lifepluslinux.blogspot.com/2018/01/hacking-facenet-using-adversarial.html>)

Author: Suresh Alse (noreply@blogger.com)

Published: 2018-01-11T23:29:00Z

Content type: tutorial

Language: en

Sources: [Life Plus Linux](<https://devfeed.tech/sources/life-plus-linux.md>)

Topics: [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Security Attacks](<https://devfeed.tech/topics/security-attacks.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>)

Tags: [authentication](<https://devfeed.tech/tags/authentication.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [deeplearning](<https://devfeed.tech/tags/deeplearning.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [face-recognition](<https://devfeed.tech/tags/face-recognition.md>), [hacking](<https://devfeed.tech/tags/hacking.md>), [ml](<https://devfeed.tech/tags/ml.md>), [neural](<https://devfeed.tech/tags/neural.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

This tutorial explains how FaceNet performs face recognition using embeddings and triplet loss, then demonstrates generating small adversarial noise intended to make an attacker's photo be identified as a target.

### Source excerpt

With the rise in popularity of face recognition systems with deep learning and it's application in security/ authentication, it is important to make sure that it is not that easy to fool them. I recently finished the 4th course on deeplearning.ai where there is an assignment which asks us to build a face recognition system - FaceNet. While I was working on the assignment, I couldn't stop thinking about how easy it is to fool it with adversarial examples. In this post I will tell you how I managed to do it. First off, some basics about FaceNet. Unlike image recognition systems which map every image with a class, it is not possible to assign a class label to every face in face recognition. This is because one, there are way too many faces that a system should handle in the real world to assign class to each of them and two, if there are new people the system should handle, it can't do it. So, what we do is, we build a system that learns similarities and dissimilarities. Basically, there is a neural network similar to what we have in image recognition and instead of applying softmax in the end, we just take the logits as embedding for the given image input and then minimize something called the triplet loss. Consider face A, we have a positive match P and negative match N. If f is the embedding function and L is the triplet loss, we have this: Triplet loss Basically, it is incentivizing small distance between A - P and large distance between A - N. Also, I really recommend watching Ian Goodfellow's lecture from Stanford's CS231n course if you want to know about adversarial examples. Like I said earlier, this thought came to me while doing an assignment from 4th course from deeplearning.ai which can be found here and I have built on top of it. The main idea here is to find small noise that when added to someone's photo although causing virtually no visual changes, can make faceNet identify them as the target. Benoit (attacker) Add noise Kian Kian Actual (Target) First l