This paper introduces InceptionRAG, a stealthy attack mechanism that subverts the standard attack paradigm of RAG, and shows superior evasion capabilities, effectively bypassing established defenses that mitigate traditional single-document injections.
Abstract
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but have been demonstrated to be vulnerable to corpus poisoning. Existing poisoning attacks against RAG largely focus on single-point explicit injection, where the malicious payload is fully encapsulated within a single document. Consequently, recent mitigation mechanisms have evolved to identify and diminish these threats effectively. In this paper, we first verify that existing mitigation mechanisms are insufficient for a new class of threats: indirect logic induction. Motivated by this observation, we introduce InceptionRAG, a stealthy attack mechanism that subverts the standard attack paradigm. Instead of injecting explicit malicious payloads, InceptionRAG fragments it into a chain of dormant passages. These passages appear harmless and can bypass existing mitigation mechanisms when examined separately. However, when retrieved together, they trigger LLMs to self-deduce target misinformation via multi-hop reasoning. To further improve the applicability of InceptionRAG in black-box settings, we propose zeroth-order suffix optimization (ZOSO) to automate the generation of authoritative suffixes. Extensive evaluations across three datasets and three LLMs demonstrate that InceptionRAG achieves an attack success rate exceeding 80% even under rigorous adversarial constraints. In particular, InceptionRAG shows superior evasion capabilities, effectively bypassing established defenses that mitigate traditional single-document injections. Our findings expose a concerning paradox: the stronger reasoning capabilities of LLMs increase their vulnerability to reasoning-based poisoning attacks. To mitigate potential misuse, we propose a document isolation-based defense, HODOR, which decouples adversarial logical dependencies.
ToxicRAG is presented, a one-document-per-target attack that expresses misinformation as a coherent knowledge-update narrative that matches or exceeds the strongest evaluated baseline in every combination of dataset--model combinations.
Hao-Zhe Lu, Jia-Qiang Li, Xin-Yuan Zhu et al.· 1 citation
KFS-RAG is proposed, a defense that mitigates information leakage by reformulating the retrieved context by identifying a small set of influential keywords from the retrieved context via an attention rollout plus a causal perturbation mechanism.
Ziliang Zhang, Yu-Bo Zhu, Wei Tong et al.· 0 citations
Two universal tool-based defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to identify and remove suspicious tools, and Normal Tool Recalling, a white-box method that restores the agent's original toolset prior to planning.
Att2RAG is presented, a double-condition framework for knowledge poisoning attacks on RAG systems that decomposes a successful poisoning event into a retrieval condition and a generation condition, and casts poisoning as maximizing attack success subject to satisfying both conditions.
Zhize Hao· Poster Volume 0008 The 2026...· 0 citations
This survey presents a unified and pipeline-aware overview of RAG robustness, formalize threat models over the corpus, retriever, and generator, and organize attacks into three main objectives: accuracy, privacy, and fairness.
Minh Tran, Cuong Dang, Tuc Nguyen et al.· 1 citation
The Tri-Layer Sieve is presented, a middleware defense that sanitizes retrieved evidence through cross-embedding-space clustering with an independent judge model, structural filtering of trigger-payload artifacts, and LLM consistency verification, and exploits a key weakness of retrieval-stage poisoning.
Muhaimin Bin Munir, Akib Jawad Ononto, Nazia Shehnaz Joynab et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.