5 papers
Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models
Tongyan Hu, Hao Li, Xiaogeng Liu +8
Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks in large language models at scale. Current methods either dr…
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Rui Yang, Junjie Xu, Zhengyu Liu +4
Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may…
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Rui Yang, Yang Hong, Yichao Xu +3
Cybersecurity assistance is dual use, requiring decisions about when to answer, limit, or refuse a request. Prior work studies refusal evaluation and conversational jailbreaking, b…
Buzz to Boom: Detecting Message Progression Vulnerabilities in Electron Applications via Segmented Directed Fuzzing
Jianjia Yu, Zhengyu Liu, Ziyang Li +2
Electron is a popular framework for building cross-platform desktop applications using web technologies. Such applications consist of multiple processes with different privilege le…
Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
Neil Fendley, Zhengyu Liu, Aonan Guan +2
Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code…