Adrian Johannes Staeves, Mayur Rattan Jaisinghani, Rebekah Overdorf, Frank Breitinger
原文摘要
AI systems increasingly appear in criminal investigations as tools, targets, and sources of evidence, yet AI forensics lacks a systematic account of the artifacts they produce: investigators often do not know which traces to look for, and for many traces they do find, no established analysis technique exists. In this paper we first developed the Forensic AI Life Cycle (FALC) that unlike other life cycle models shifts the focus onto the forensic artifacts created during the life cycle of an AI system. Through FALC we derived a reference list of artifacts that might serve an investigation. Second, we collected examples for crimes with AI involvement throughout FALC and questions likely to be asked when investigating these crimes. Third, we propose a taxonomy of forensic fields of expertise with a focus on the current possibility to analyze AI forensic artifacts using established techniques. For investigators, the model provides a systematic basis for identifying which artifacts to look for when an AI system is relevant to a case. For researchers, the classification shows where existing forensic methods already suffice and where new techniques are most urgently needed.
Aruna Withanage, Jessica Herrmann, Hudan Studiawan, Frank Breitinger
原文摘要
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.