2026
[MAR] Our paper “Adversarial Hubness in Multi-Modal Retrieval” is accepted to appear in 47th IEEE Symposium on Security and Privacy (IEEE S&P) 2026, see you in San Francisco!
[Feb] Our paper “Adversarial Decoding: Generating Readable Documents for Adversarial Objectives” is accepted to appear in Findings of the European Chapter of the Association for Computational Linguistics: EACL (Findings of EACL) 2026!
2025
[OCT] Passed my qualification exam titled “Vulnerabilities in Multi-Modal Representations” and became a Ph.D. candidate!
[Aug] Gave a talk titled “Exposing and Exploiting Vulnerabilities in Multi-Modal Representations” at the AI Security Seminar at the University of Massachusetts.
[Jun] Our paper “Self-interpreting Adversarial Images” is accepted to appear in USENIX Security Symposium (USENIX Security) 2025, see you in Seattle!
[Apr] Invited talk titled “Adversarial Illusions in Multi-Modal Embeddings” at RSAC 2025.
2024
[Dec] Gave a talk titled “Attacking and Defending Multi-Modal Representations” at the Security Seminar at the University of Virginia.
[Aug] We are thrilled and honored that our paper received the Distinguished Paper Award at USENIX Security 2024.
[Jun] Our paper “Adversarial illusions in multi-modal embeddings” is accepted to appear in USENIX Security Symposium (USENIX Security) 2024, see you in Philadelphia!
2023