Newest papers

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

Frank Breitinger, Jan Gruber, Christopher Hargreaves, Jan-Niclas Hilgert, Gaëtan Michelet, Mark Scanlon · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29747 · cited by 0 works (OpenAlex) · open-access PDF

Korean

대형 언어 모델 (LLMs)는 검사 조수와 자율 요원으로 디지털 법학에 들어가고 있습니다. 디지털 법학은 간접 프롬프트 주입을위한 일반적인 설정을 반환합니다 : 분석 중인 증거는 정의로 공격자 통제되며 검사자는 그것을 자세히 읽어야합니다. 이것은 검사 층을 데이터 및 도구의 고전적인 것들 옆에 새로운 항법학적 표적으로 만듭니다. 고전적인 항법학적 지표는 그것을 덮지 않으며 즉시 주입 방어는 그것을 예측하지 않습니다. 우리는 논의의 조작을 반영하기 위해 항법학적 모델을 확장하고, 적대적 증거를 통해 수행되는 공격의 새로운 수율론을 제시합니다 : 공격자는 목표, 기술, 유

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) are entering digital forensics as examination assistants and autonomous agents. Digital forensics inverts the usual setting for indirect prompt injection: the evidence under analysis is attacker-controlled by definition, and the examiner is obliged to read it closely. This makes the reasoning layer a new anti-forensic target, next to the classical ones of data and tools. Classical anti-forensic taxonomies do not cover it, and prompt injection defences do not anticipate it. We extend the anti-forensic model to reflect the manipulation of reasoning, and present a taxonomy of attacks carried through adversarial evidence: an attacker selects an objective, a technique, a payload location, and a concealment method. We observe a perception gap, i.e., the fact that deterministic tools, the human examiner, and the model perceive the same evidence differently, which is what lets an injection reach the model unseen by the examiner. We demonstrate three attacks against an LLM-assisted analysis pipeline, changing a reported conclusion, writing attacker-chosen content to the analyst's workstation, and causing outbound network traffic, each driven only by text planted on the seized device. Mitigations to these attacks are also proposed.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Adversarial system, Taxonomy (biology), Computer security, Digital evidence, Digital forensics

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange