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
arXiv:2606. 09700v1 Announce Type: cross Abstract: Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content.
By Qin Yang, Lu Malloy, Joshua Lee, Xiaohan Chang, Meisam Mohammady, Doowon Kim, Yuan Hong
arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.
By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan 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
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
By Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
EvoHarmBench is a dynamic adversarial evaluation framework that simulates how users iteratively modify harmful content to evade moderation. It uses an optimization loop that evolves evasion strategies at the semantic-cluster level while maintaining human readability, and tests 229 semantic sub-clusters across five violation categories derived from 5,002 real-world adversarial samples. The study shows that even state‑of‑the‑art LLM‑based moderators can be bypassed with an 80.3% success rate after twelve iterations, highlighting significant vulnerabilities in current systems.
By Ruijie Jian, Benlei Cui, Ting Ma, Haidong Ding, Kangwei Liu, Ziwen Xu, Longtao Huang, Hui Xue, Ziqiang Zhu, Junjie Li, Haiwen Hong