Prompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital Investigations

Summary

This research paper examines how attacker-controlled evidence can manipulate LLMs used in digital forensics, extending anti-forensic models to cover the reasoning layer. It proposes a taxonomy of attacks built from an objective, a technique, a payload location and a concealment method, and attributes the gap to a perception difference between deterministic tools, the human examiner and the model. The authors demonstrate three attacks against an LLM-assisted analysis pipeline that alter a reported conclusion, write attacker-chosen content to the analyst's workstation and cause outbound network traffic, each triggered only by text planted on a seized device.

Mitigation

Mitigations to these attacks are also proposed.

Topics

• Prompt injection and jailbreaks

Related items

• InfoIs Claude Code safe for the enterprise? What the official settings cover, and what they don'tSimilar attack · Adversa AI Blog
• Info‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake TargetsSimilar attack · SecurityWeek
• InfoThe Harness Is the Hard Part of Agentic PentestingSimilar attack · The Hacker News
• InfoWhere AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden VulnerabilitiesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoCorrelated Failures of AI Approval MonitorsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)