14 papers
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
Shihao Weng, Yang Feng, Xiaofei Xie +1
Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user r…
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
Shihao Weng, Yang Feng, Jinrui Zhang +3
Large Language Model (LLM) agents are increasingly deployed as task-oriented software systems that use runtime context to decide and act on behalf of users. This delegation model m…
Weaponizing the Commons: A Taxonomy and Detection Framework of Abuse on GitHub
Yuli Cheng, Xiaoyu Zhang, Jiongchi Yu +3
GitHub plays a critical role in modern software supply chains, making its security an important research concern. Existing studies have primarily focused on CI/CD automation, colla…
Human in the Loop for Fuzz Testing: Literature Review and the Road Ahead
Jiongchi Yu, Xiaolin Wen, Sizhe Cheng +3
Fuzz testing is one of the most effective techniques for detecting bugs and vulnerabilities in software. However, as the basis of fuzz testing, automated heuristics often fail to u…
DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
Yu Li, Qiang Hu, Yao Zhang +3
Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent,…
PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems
Jiongchi Yu, Yuhan Ma, Xiaoyu Zhang +4
With the increasing deployment of large language models (LLMs) in affective agents and AI systems, maintaining a consistent and authentic LLM personality becomes critical for user…