VerTox is a framework that turns corpus poisoning of neural ranking models into a verifiable reward‑guided reinforcement learning problem. By fine‑tuning compact large language models with reward shaping that couples ranking distortion and factual corruption, VerTox generates fluent, low‑perplexity adversarial documents that frequently outrank target items across multiple ranking architectures, including a commercial embedding model. Experiments show near‑perfect attack success and significant degradation of downstream retrieval‑augmented generation performance.
By Zhiqi Huang, Vivek Datla, Zhichao Xu, Puxuan Yu, Vivek Srikumar, Alfy Samuel
arXiv:2605.29224v2 Announce Type: replace-cross
Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incor...
By Aditya Nawal, Manit Baser, Mohan Gurusamy
arXiv:2606. 25476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness.
By Abrar Alotaibi, Raed Mughus, Moataz Ahmed
arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.
By Shawn Li, Yue Zhao
arXiv:2606. 11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection.
By Xi Nie, Hongwei Li, Shenghao Wu, Mingxuan Li, Jiachen Li, Wenbo Jiang
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
By Maryam Hashemzadeh, Jerry Huang, Minseon Kim, Marc-Alexandre C\^ot\'e, Sarath Chandar
RAGSentinel is a training‑free, label‑free defense designed for black‑box retrieval‑augmented generation systems. It employs a surrogate encoder to detect hidden‑state shifts caused by retrieved documents, removes shared topic directions, and filters poisoned documents as geometric outliers from a robust majority consensus. The method is proven to recover a poison‑free majority context under honest‑majority and representation‑separation assumptions, and experiments show it keeps attack success rates low while maintaining accuracy across multiple datasets, LLM families, and adaptive attacks.
By Yueyang Quan, Anjun Gao, Yufei Xia, Minghong Fang, Zhuqing Liu
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
By Md. Hasib Ur Rahman
arXiv:2608. 04286v1 Announce Type: cross Abstract: Large language models (LLMs) are often used in conjunction with external knowledge sources to improve their factual accuracy and decrease hallucinations, through methods such as Retrieval-Augmented Generation (RAG).
By Atri Vivek Sharma, Brian Formento, Alessio Lomuscio
arXiv:2607. 13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard.
By Dima Galat, Marian-Andrei Rizoiu
The paper introduces Trustworthy RAG, an evaluation agent designed to detect misinformation and knowledge poisoning in Retrieval-Augmented Generation systems. It combines natural language inference verification, a five-signal poison detector, and a weighted Trust Index to assess the reliability of retrieved content. Experiments on multiple LLMs show high accuracy and precision, with the agent effectively blocking unsafe advice in a secure-coding assistant scenario.
By Balkrishna Giri, Md Toufique Hasan, Jussi Rasku, Muhammad Waseem, Pekka Abrahamsson
arXiv:2602. 14307v4 Announce Type: replace Abstract: As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers, or evaluate complex solutions.
By Samuele Marro, Jialin Yu, Emanuele La Malfa, Oishi Deb, Jiawei Li, Yibo Yang, Ebey Abraham, Sunando Sengupta, Eric Sommerlade, Michael Wooldridge, Philip Torr