Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although streaming probes enable real-time monitoring, they still make systematic errors. We identify a core issue: existing methods often rely on a few high-scoring tokens, leading to false alarms when sensitive CBRN terms appear in benign contexts. To address this, we introduce a streaming probing objective that requires multiple evidence tokens to consistently support a prediction, rather than relying on isolated spikes. This encourages more robust detection based on aggregated signals instead of single-token cues. At a fixed 1% false-positive rate, our method improves the true-positive rate by 35.55% relative to strong streaming baselines. We further observe substantial gains in AUROC, even when starting from near-saturated baseline performance (AUROC = 97.40%). We also show that probing Attention or MLP activations consistently outperforms residual-stream features. Finally, even when adversarial fine-tuning enables novel character-level ciphers, harmful intent remains detectable: probes developed for the base LLMs can be applied ``plug-and-play'' to these obfuscated attacks, achieving an AUROC of over 98.85%.
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
Georgia Institute of Technology(佐治亚理工学院);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);UCSD(加州大学圣地亚哥分校);National Taiwan University(台湾大学);IBM Research(IBM研究院);Virtue AI
School of Computer Science and Technology, Guangdong University of Technology(广东工业大学计算机科学与技术学院);School of Computer Science and Intelligence Education, Lingnan Normal University(岭南师范学院计算机与智能教育学院);College of Computer, National University of Defense Technology(国防科技大学计算机学院);School of Information Science and Technology, Guangdong University of Foreign Studies(广东外语外贸大学信息科学与技术学院)
Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt(德累斯顿技术大学计算机科学系、海斯堡人工智能中心(hessian.AI)、通用知识处理实验室(UKP Lab))
针对推理驱动的隐蔽越狱漏洞,本文提出 POATE 对比推理攻击,并设计 Intent-Aware CoT 与 Reverse Thinking CoT 以检测恶意意图、拒绝有害输出。
Strategic Deflection: Defending LLMs from Logit Manipulation
International Artificial Intelligence Center of Morocco(摩洛哥国际人工智能中心);Mohammed VI Polytechnic University(摩洛哥穆莱·伊斯梅尔理工学院);AgriEdge;Sorbonne University, LIP6 - UMR 7606 CNRS(索邦大学,LIP6 - UMR 7606 CNRS)
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
Boise State University(博伊州立大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Pittsburgh(匹兹堡大学);New York University(纽约大学);Florida International University(佛罗里达国际大学)
How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
School of Computer Science and Technology Xi’an Jiaotong University China(西安交通大学计算机科学与技术学院);Shanghai AI Laboratory(上海人工智能实验室);MOE KLINNS Lab Xi’an Jiaotong University China(西安交通大学教育部KLINNS实验室)
Conversational Complexity for Assessing Risk in Large Language Models
University of Cambridge(剑桥大学);Spanish National Research Council(西班牙国家研究委员会);Universitat Politècnica de València(瓦伦西亚理工大学);Leverhulme Centre for the Future of Intelligence(勒沃休姆未来智能中心);Center for Automation and Robotics(自动化与机器人中心);Valencian Research Institute for Artificial Intelligence(瓦伦西亚人工智能研究所)
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
LMU Munich(慕尼黑大学);relAI – Konrad Zuse School of Excellence in Reliable AI(relAI – 康拉德·楚泽可靠人工智能卓越学校);University of Pisa(比萨大学);Munich Center for Machine Learning(慕尼黑机器学习中心);School of Engineering, Computing and Mathematics, Oxford Brookes University(牛津布鲁克斯大学工程、计算与数学学院)
SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme Detection
University of California, San Diego(加利福尼亚大学圣迭戈分校);Xi’an Jiaotong-Liverpool University(西交利物浦大学);University of Washington(华盛顿大学);The Australian National University(澳大利亚国立大学);Zhejiang University(浙江大学)