conference

PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
Private deep neural network (DNN) inference based on secure twoparty computation (2PC) enables secure privacy protection for both the …
Tianshi Xu, Shuzhang Zhong, Wenxuan Zeng, Runsheng Wang, Meng Li
Paper Link
FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference
With the fast evolution of large language models (LLMs), privacy concerns with user queries arise as they may contain sensitive …
Chenqi Lin, Tianshi Xu, Zebin Yang, Runsheng Wang, Ru Huang, Meng Li
PDF Paper Link
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant …
Tianshi Xu, Lemeng Wu, Runsheng Wang, Meng Li
PDF Code Paper Link
Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference
Efficient networks, e.g., MobileNetV2, EfficientNet, etc, achieves state-of-the-art (SOTA) accuracy with lightweight computation. …
Tianshi Xu, Meng Li, Runsheng Wang, Ru Huang
PDF DOI Paper Link