Jin Tan

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference

Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference

Nimbus: Secure and Efficient Two-Party Inference for Transformers

Ditto: Quantization-Aware Secure Inference of Transformers upon MPC

PUMA: Secure Inference of LLaMA-7B in Five Minutes