StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
School of Software Technology, Zhejiang University（浙江大学软件学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）
Huawei Zheng, Xinqi Jiang, Sen Yang, Shouling Ji, Yingcai Wu, Dazhen Deng
Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risks. Domain-specific datasets of harmful prompts remain scarce and still largely rely on manual construction; public datasets mainly focus on explicit harmful prompts, which modern LLM defenses can often detect and refuse. In contrast, implicit harmful prompts-expressed through indirect domain knowledge-are harder to detect and better reflect real-world threats. We identify two challenges: transforming domain knowledge into actionable constraints and increasing the implicitness of generated harmful prompts. To address them, we propose an end-to-end framework that first performs knowledge-graph-guided harmful prompt generation to systematically produce domain-relevant prompts, and then applies two-strategy obfuscation rewriting to convert explicit harmful prompts into implicit variants via direct and context-enhanced rewriting. This framework yields high-quality datasets combining strong domain relevance with implicitness, enabling more realistic red-teaming and advancing LLM safety research. We release our code and datasets on GitHub.
SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Toronto Metropolitan University（多伦多都会大学）；IIT, Roorkee（印度理工学院鲁尔基分校）；University of Michigan（密歇根大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术全国重点实验室）；Meituan Inc.（美团公司）；Dalian University of Technology（大连理工大学）
From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Shanghai University of Electric Power（上海电力大学）；School of Information Science and Engineering, East China University of Science and Technology（东华大学信息科学与工程学院）
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
BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning
The Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）；Shenzhen University（深圳大学）；Shenzhen Loop Area Institute（深圳河套学院）
Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models
Beijing Key Lab of Traffic Data Analysis and Mining（北京交通大数据分析与挖掘重点实验室）；Beijing Jiaotong University（北京交通大学）；School of Information Technology and Management（信息科技与管理学院）；University of International Business and Economics（国际经济贸易大学）
MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
University of Waterloo（滑铁卢大学）；National University of Singapore（新加坡国立大学）；University of California, Merced（加州大学默塞德分校）；University of Alberta（阿尔伯塔大学）；University of Queensland（昆士兰大学）
Detect, Investigate, Judge and Determine: A Knowledge-guided Framework for Few-shot Fake News Detection
University of Science and Technology of China（中国科学技术大学）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；The Hong Kong University of Science and Technology（香港科技大学）
