Get started
Author

Yunhao Feng

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
2026 · Feng, Yunhao, Ding, Yifan, et al. · arXiv (Cornell University) · 27
PDF
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
2026 · Yunhao Feng, Yifan Ding, et al. · ACM International Conference on Multimedia (ACM MM) · 20
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
2026 · Lin, Ruixiao, Deng, Xinhao, et al. · arXiv (Cornell University) · 20
PDF
Experimental and Theoretical Studies of Action Mechanism of an Octadecylamine-based Molecular Assembly on Mild Steel†
2019 · Yucong Ma, Baomin Fan, et al. · 高等学校化学学报 · 17
BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
2026 · Feng, Yunhao, Li, Yige, et al. · arXiv (Cornell University) · 15
PDF
A Multitask Learning-Based Model for Gas Classification and Concentration Prediction
2024 · Yang Dai, Yin Xiong, et al. · IEEE Sensors Journal · 13
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
Analysis of Motion Characteristics of Bionic Morphing Wing Based on Sarrus Linkages
2022 · Zhong Yun, Yunhao Feng, et al. · Applied Sciences · 9
PDF
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
2026 · Feng, Yunhao, Du, Xiaohu, et al. · arXiv (Cornell University) · 7
PDF
The design and evaluation of the outflow structures of an interventional microaxial blood pump
2023 · Zhong Yun, Jinfu Yao, et al. · Frontiers in Physiology · 7
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
A novel model for hemolysis estimation in rotating impeller blood pumps considering red blood cell aging
2023 · Liang Wang, Zhong Yun, et al. · Frontiers in Physiology · 6
PDF
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents
2026 · Ma, Jianan, Du, Xiaohu, et al. · arXiv (Cornell University) · 5
PDF
Constitutional On-Policy Safe Distillation
2026 · Wen, Ming, Liu, Yuxuan, et al. · arXiv (Cornell University) · 4
PDF
BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
2026 · Yunhao Feng, Yige Li, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 4
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
2026 · Feng, Yunhao, Lin, Ruixiao, et al. · arXiv (Cornell University) · 2
PDF
TADSOB: Enhancing jailbreaking attacks on LLMs via trajectory-aware dynamic suffix optimization with buffer
2026 · Xiaolong Li, Mingrui Lao, et al. · Neurocomputing · 1
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
2026 · Chen, Jialuo, Wang, Minghe, et al. · arXiv (Cornell University) · 1
PDF
Position: AI Safety Requires Effective Controllability
2026 · Li, Yige, Feng, Yunhao, et al. · arXiv (Cornell University) · 1
PDF
MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents
2026 · Wang, Zhihua, Feng, Yunhao, et al. · arXiv (Cornell University)
PDF
CST: Lightweight Risk Triage with Source-Grounded Evidence for Web Discussions
2026 · Wang, Zhihua, Gao, Yifeng, et al. · arXiv (Cornell University)
PDF
Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents
2026 · Zeng, Detao, Ou, Guilin, et al. · arXiv (Cornell University)
PDF
ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
2026 · Zhai, Kun, Li, Teng, et al. · arXiv (Cornell University)
PDF
AdaGuard: An Adaptive Guard Model with User-defined Policies
2026 · Feng, Yunhao, Ding, Yifan, et al. · arXiv (Cornell University)
PDF
JAIL: Adaptive multi-turn jailbreak attacks reveal limitations of LLM safety alignment
2026 · Yunhao Feng, Mingrui Lao, et al. · Expert Systems with Applications
Works count: 30
Citation count: 174
H-index: 8
I10-index: 6
Year
Topic
Type