PhD Student
European Association for Computational Linguistics (EACL)
Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language Models
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
Conference on Empirical Methods in Natural Language Processing (EMNLP)
The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective
Usenix Security Symposium (USENIX-Security)
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
Usenix Security Symposium (USENIX-Security)
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots