Research
[PDF] CamoDocs: A Poisoning Attack Against Retrieval-Augmented ...
Publication date unknown · Discovered aclanthology.org
Page published
Publication date unknown · First observed: 7 Nov 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
CamoDocs demonstrates that RAG poisoning defenses built around query overlap or tight embedding clusters can miss camouflaged malicious documents, while stronger filtering can impair legitimate retrieval.
CamoDocs is a RAG poisoning technique that camouflages adversarial documents using benign content and dispersion tokens, avoiding query-overlap and embedding-clustering signals used by defenses. The paper evaluates seven defenses across three benchmarks and reports attack success rates of 61.80% against GPT-5.4-mini and 55.09% against Claude-Haiku-4.5. Aggressive clustering defenses reduced attack success but substantially degraded retrieval-dependent utility.