Get started
Author

Xinhao Deng

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
2026 · Deng, Xinhao, Zhang, Yixiang, et al. · arXiv (Cornell University) · 39
PDF
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
2026 · Feng, Yunhao, Lin, Ruixiao, et al. · arXiv (Cornell University) · 9
PDF
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
2026 · Feng, Yunhao, Du, Xiaohu, et al. · arXiv (Cornell University) · 7
PDF
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills
2026 · Liu, Mingxiao, Jiang, Zhoumian, et al. · arXiv (Cornell University) · 6
PDF
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
2026 · Chen, Jialuo, Jiang, Lingqi, et al. · arXiv (Cornell University) · 6
PDF
Automating Agent Hijacking via Structural Template Injection
2026 · Deng, Xinhao, Wu, Jiaqing, et al. · arXiv (Cornell University) · 6
PDF
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents
2026 · Ma, Jianan, Du, Xiaohu, et al. · arXiv (Cornell University) · 5
PDF
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
2026 · Feng, Yunhao, Lin, Ruixiao, et al. · arXiv (Cornell University) · 2
PDF
AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
2026 · Zhang, Yixiang, Deng, Xinhao, et al. · arXiv (Cornell University) · 2
PDF
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
2026 · Chen, Jialuo, Wang, Minghe, et al. · arXiv (Cornell University) · 1
PDF
Mitigating Proxy-Induced Traffic Drift in Website Fingerprinting via Model-Agnostic Traffic Tailoring
2026 · Yu, Linxiao, Cui, Tianyu, et al. · arXiv (Cornell University)
PDF
PromptEcho
2026 · Li, Sijia, Cui, Tianyu, et al. · Zenodo (CERN European Organization for Nuclear Research)
Works count: 12
Citation count: 82
H-index: 5
I10-index: 1
Year
Topic
Type