# Federated Forensics: Jurisdictional constraints as a design driver for multi-agency federated learning

DevFeed: [Federated Forensics: Jurisdictional constraints as a design driver for multi-agency federated learning](<https://devfeed.tech/articles/federated-forensics-jurisdictional-constraints-as-a-design-driver-for-multi-agency-federated-learning-122798.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09277>)

Author: Aruna Withanage, Jessica Herrmann, Hudan Studiawan, Frank Breitinger

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Digital forensics](<https://devfeed.tech/topics/digital-forensics.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agencies](<https://devfeed.tech/tags/agencies.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [border](<https://devfeed.tech/tags/border.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [design](<https://devfeed.tech/tags/design.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [forensics](<https://devfeed.tech/tags/forensics.md>), [malware](<https://devfeed.tech/tags/malware.md>), [policy](<https://devfeed.tech/tags/policy.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [reference-architecture](<https://devfeed.tech/tags/reference-architecture.md>), [requirements](<https://devfeed.tech/tags/requirements.md>)

## AI overview

Federated Forensics addresses jurisdictional and accountability rules that federated learning alone does not enforce. The paper derives seven forensic requirements and proposes a three-layer architecture with a middle layer at jurisdictional borders: it can use a model update locally while preventing restricted updates from crossing. In a prototype evaluated on malware-family classification, the policy gate blocked all restricted updates with zero violations. Restricted-class accuracy reached 93.0%, compared with 0% under the compliant alternative described and 4.4 percentage points below ignoring the restriction. These are prototype results; the supplied abstract does not establish performance in operational investigations.

## Source excerpt

arXiv:2611.09277v1 Announce Type: new Abstract: Digital forensic investigations increasingly cross borders, and law enforcement agencies need to build analytical models together without centralizing their data. Federated Learning (FL) keeps data local, yet neither FL nor its frameworks enforce the jurisdictional, governance, and accountability rules that multi-agency forensic work requires. This paper takes a design-first approach to that gap. First, we derive seven requirements that a federated learning system must meet in a forensic setting. Second, we propose Federated Forensics, a three-layer reference architecture whose middle layer, unlike in existing hierarchical FL designs, sits at a jurisdictional border and can use a model update locally while blocking it from crossing that border. Third, we build a prototype of the architecture and test it on a malware-family classification task. In a prototype evaluation, the policy gate blocked every restricted update at the border with zero violations, and restricted-class accuracy rose from 0% under today's compliant alternative to 93.0%, only 4.4 points below ignoring the restriction.