Problem
Research questions and friction points this paper is trying to address.
AI forensics
post-incident investigation
access levels
evidence preservation
chain of custody
AI Forensics Across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems
🤖 AI Summary
This study addresses the absence of a unified investigative framework for AI system incidents, which hinders behavior reconstruction, accountability attribution, and supply chain traceability. It proposes the first AI forensics process model structured around investigators’ levels of system access—white-box, gray-box, and black-box—and organized into four phases: collection, preservation, analysis, and reporting. The work introduces a method for ranking evidence volatility and integrates multi-source data—including logs, context windows, retrieval corpora, and training lineages—into a structured forensic workflow matrix. By clarifying critical open issues such as black-box evidence preservation and model version authentication, the paper identifies four core challenges and establishes a theoretical foundation for designing auditable and accountable AI systems.
📝 Abstract
AI systems are increasingly involved in decisions and actions that may later require investigation. When an AI related incident occurs, investigators need to reconstruct what the system did, why it behaved that way, and which part of the system or supply chain contributed to the outcome. Existing work on AI forensics remains fragmented, often focusing on a specific system type, artifact, or analysis technique. This paper argues that investigator access is a useful starting point for organizing the field. We distinguish white box, grey box, and black box access and show how each access level changes what can be collected, preserved, analyzed, and reported. Based on this distinction, we propose a process model matrix for AI forensics across four phases: collection, preservation, analysis, and reporting. We also introduce an order of volatility for AI systems, covering runtime state, context windows, logs, retrieval stores, model artifacts, and training lineage. From this matrix, we derive an access conditioned examination framework and identify open research problems, including black box preservation, model version attestation, uncertainty quantification for surrogate based analysis, and chain of custody for mutable AI artifacts.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI forensics
access levels
process model
order of volatility
chain of custody
🔎 Similar Papers
No similar papers found.
