一篇论文被IEEE S&P (Oakland)接收
一篇关于隐私保护生成式大语言模型推理的论文被IEEE Symposium on Security and Privacy (S&P/Oakland)接收。
论文题目为“Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache”。该工作由Ye Yu主导。
一篇关于隐私保护生成式大语言模型推理的论文被IEEE Symposium on Security and Privacy (S&P/Oakland)接收。
论文题目为“Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache”。该工作由Ye Yu主导。