Publications

Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu, Yifeng Cai, Hamed Haddadi (2025). Membership and Memorization in LLM Knowledge Distillation. In EMNLP 2025.

Hwiwon Lee, Ziqi Zhang, Hanxiao Lu, Lingming Zhang (2025). SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks. to appear In NeurIPS 2025.

Hanxiao Lu, Hongyu Cai, Yiming Liang, Antonio Bianchi, Z. Berkay Celik (2025). A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer. In SANER 2025.

Hanxiao Lu, Zeyu Huang, Ren Wang (2025). Purification of contaminated convolutional neural networks via robust recovery: An approach with theoretical guarantee in one-hidden-layer case. In JSTSP 2025.

Hanxiao Lu, Zeyu Huang, Ren Wang (2023). Enhancing Healthcare Model Trustworthiness Through Theoretically Guaranteed One-Hidden-Layer CNN Purification. In ICLR workshop TML4H 2023.