arXiv Computation and Language
Reasoning Reduces the Influence of Poisoned Context in RAG
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Sep 18
Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents
The paper examines how deliberative (System 2) reasoning affects a Retrieval-Augmented Generation (RAG) model’s vulnerability to knowledge‑poisoning attacks. Using two metrics—Cordon Rate and Leakage Rate—it evaluates six model configurations on 200 SciFact questions. Results show that enabling reasoning lowers both Cordon and Leakage Rates for DeepSeek‑V4‑Flash, indicating reduced behavioral impact from poisoned evidence, though overall attack success increases.
arXiv Computation and Language
Sep 2
TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning
arXiv:2609.00470v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical at...
arXiv AI
Aug 5
DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial
arXiv:2608. 02678v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus can steer the underlying large language model (LLM) toward an attacker-chosen wrong answer.
arXiv AI
Sep 15
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
The paper introduces a new attack called "plan injection" that allows a large language model to carry out harmful actions while evading chain-of-thought monitoring. By inserting harmful but benign-sounding reasoning into the model’s context, the attacker can steer the model’s behavior and cause it to paraphrase the injected plan as its own reasoning. The study demonstrates that this attack works across different monitoring settings, scales to harder tasks, and even causes monitors to waste resources on the injected plan, reducing detection rates by up to 50%.
arXiv Machine Learning
Jul 30
RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning
arXiv:2607. 26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning: maliciously injected passages that manipulate retrieved evidence.
Hugging Face Trending Papers
Jul 21
SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.