arXiv:2609.09243v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: i...
By Iliano Fasolino
arXiv:2608.17153v3 Announce Type: replace
Abstract: Retrieval-Augmented Generation (RAG) improves large language models by grounding them in external evidence, but this exposes them to knowledge-pois...
By Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim, Hamidreza Baradaran Kashani
TAME (Token Attribution and Masking for Emergent misalignment) is a three‑stage framework that identifies which training tokens drive harmful behavior in fine‑tuned language models. It first scores tokens by how much fine‑tuning increases their likelihood, then characterizes patterns among high‑attribution tokens, and finally validates them by masking during training. Experiments on Llama and Qwen show that masking the top‑attribution tokens reduces emergent misalignment by 23‑ to 36‑fold, while random masking has no effect.
By Md Rayhanul Masud, Md Rizwan Parvez
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.
By Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim, Hamidreza Baradaran Kashani
Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignment (EM). Prior work has localized EM in model weig...
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.
By Abay Zhurekbay, Tao Liu, Fan Li