Skip to content

InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation

Sep 2026 · arXiv.org · Vol abs/2609.16818 · 1 citation · 52 references
Computer Science

TL;DR

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.

View source

Similar papers

Conference 2026

Att2RAG: A Double-Condition Framework for Knowledge Poisoning Attacks on RAG Systems

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 · 0 citations
#natural language process... Preprint Aug 2026

TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning

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.