Tianshi Xu

PhD Student (2023)

Peking University

兴趣爱好
  • Efficient and Private AI Algorithm & Protocol
教育经历

  • B.S. in Software Enigneering, 2023

    Beihang University

Publications

Tianshi Xu, Wenjie Lu, Jiangrui Yu, Chenqi Lin, Yi Chen, Runsheng Wang, 李萌 (2025). Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC. In Usenix Security Symposium 2025.

论文

Tianshi Xu, Lemeng Wu, Runsheng Wang, 李萌 (2024). PrivCirNet: Efficient Private Inference via Block Circulant Transformation. In Conference on Neural Information Processing Systems (NeurIPs) 2024.

论文

Jiangrui Yu, Wenxuan Zeng, Tianshi Xu, Renze Chen, Yun (Eric) Liang, Runsheng Wang, Ru Huang, 李萌 (2024). FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference. In International Conference on Computer-Aided Design (ICCAD) 2024.

论文

Tianshi Xu, Shuzhang Zhong, Wenxuan Zeng, Runsheng Wang, 李萌 (2024). PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization. In International Conference on Computer-Aided Design (ICCAD) 2024.

论文

Chenqi Lin, Tianshi Xu, Zebin Yang, 李萌, Runsheng Wang, Ru Huang (2024). FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference. In Design Automation Conference (DAC) 2024.

论文

Tianshi Xu, 李萌, Runsheng Wang, Ru Huang (2023). Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference. In ACM/IEEE International Conference on Computer Aided Design (ICCAD) 2023.

论文

Yu Fu, Yu Tong, Yijing Ning, Tianshi Xu, 李萌, Jingqiang Lin, Dengguo Feng (0001). Swift: Fast Secure Neural Network Inference with Fully Homomorphic Encryption.