[new-research] arXiv:2608.28389 — CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using C

[github-actions]

New arXiv Research Paper

arXiv ID: 2608.28389
Title: CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
Authors: Jaewon Jung, Haizhong Zheng, Hongsun Jang, Jaeyong Song, Beidi Chen, Jinho Lee
Published: 2026-08-28T14:44:28Z
URL: https://arxiv.org/abs/2608.28389

Abstract (first 300 chars)

Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers. Existing poisoning attacks often rely on query inclusion, inserting…

Suggested OWASP Mapping

DSGAI04, LLM04

Suggested Action

Review this paper against the OWASP GenAI Crosswalk entries and update relevant mapping files if new attack patterns or mitigations are identified.