11 papers
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Yunhao Feng, Ruixiao Lin, Ming Wen +5
Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through runtime behavior rather than g…
Safety in Self-Evolving Agents: A Survey
Jiahao Chen, Zhou Feng, Oubo Ma +28
Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from new interactions. In open-end…
Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning
Fukang Zhu, Binbin Zhao, Ruixiao Lin +3
Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on…
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
Jialuo Chen, Minghe Wang, Lingqi Jiang +7
LLM-agent ecosystems are rapidly growing around reusable skills: mixed-modality packages of metadata, natural-language instructions, code, tools, references, and operational workfl…
SherAgent: Scaling Attack Investigation in the Wild via LLM-Empowered Iterative Query-Filter Backtracking
Zhenyuan Li, Zhengkai Wang, Ling Jiang +5
Provenance-based attack investigation enables viable automation by standardizing data and query logic; however, it is critically hindered in practice by dependency explosions and f…
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Yunhao Feng, Ruixiao Lin, Ming Wen +12
LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed sa…
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Ruixiao Lin, Xinhao Deng, Qingming Li +12
Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
Oubo Ma, Ruixiao Lin, Yang Dai +4
Extensive research has highlighted the severe threats posed by backdoor attacks to deep reinforcement learning (DRL). However, prior studies primarily focus on vanilla scenarios, w…
Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
Jiahao Chen, Qi Zhang, Ruixiao Lin +7
Large Language Models (LLMs) have revolutionized how information are collected, aggregated, and reasoned. However, this enables a novel and accessible vector of privacy intrusion:…
IntraGuard: Committee-Side Defenses Against Review Outsourcing to Commercial Chatbots
Oubo Ma, Ruixiao Lin, Jiahao Chen +3
LLMs become increasingly capable, editorial boards and program committees are growing concerned about reviewers who fully outsource peer review to commercial chatbots. This concern…
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents
Jianan Ma, Xiaohu Du, Ruixiao Lin +9
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Existing L…