Publications
(* denotes equal contribution)
2025
- S&PBAIT: Large Language Model Backdoor Scanning by Inverting Attack TargetIn Proceedings of the 46th IEEE Symposium on Security and Privacy, San Francisco, CA, USA, 2025
2024
- NeurIPSBiScope: AI-generated Text Detection by Checking Memorization of Preceding TokensIn Proceedings of Thirty-Eighth Conference on Neural Information Processing Systems, Vancouver, Canada, 2024
2023
- ICLRFLIP: A Provable Defense Framework for Backdoor Mitigation in Federated LearningIn Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda, 2023
2022
2021
- S&PStochFuzz: Sound and Cost-effective Fuzzing of Stripped Binaries by Incremental and Stochastic RewritingIn Proceedings of the 42nd IEEE Symposium on Security and Privacy, Virtual Event, 2021
2020
2019
- OOPSLABDA: Practical Dependence Analysis for Binary Executables by Unbiased Whole-program Path Sampling and Per-path Abstract InterpretationProceedings of the ACM on Programming Languages, Athens, Greece, 2019