3 papers
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.LG2026
A Sustainable AI Economy Needs Data Deals That Work for Generators
Ruoxi Jia, Luis Oala, Wenjie Xiong +4
We argue that the machine learning value chain is structurally unsustainable due to an economic data processing inequality: each state in the data cycle from inputs to model weight…
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…