Resume
Academic Achievements
- Recipient of Amazon Fellowship and Bilsland Dissertation Fellowship
- Published 'SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks' at USENIX Security 2025
- Published 'μKE: Matryoshka Unstructured Knowledge Editing of Large Language Models' at COLM 2025 (supervised author)
- Published 'CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling' at NDSS 2025
- Published 'Exploring the Orthogonality and Linearity of Backdoor Attacks' at IEEE S&P (Oakland) 2024
- Published 'FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning' at ICLR 2023
- Best Paper Award at ECCV 2022 Workshop on Adversarial Robustness in the Real World