Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache
Ye Yu, Yifan Zhou, Yi Chen +3
Generative large language models (LLMs) have revolutionized multiple domains. Modern LLMs predominantly rely on an autoregressive decoding strategy, which generates output tokens s…
cs.CR2025
Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities
Evan Lai, Wenjie Xiong, Edward Suh +2
Speculative attacks such as Spectre can leak secret information without being discovered by the operating system. Speculative execution vulnerabilities are finicky and deep in the…