Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
Yuhan Ma, Yong Li, Stefan Schmid
Two-server secure inference allows a client to query a hosted large language model (LLM) without revealing prompts or embeddings. Recent GPU systems based on function secret sharin…
cs.CR2026
SecureClaw: Clawing Back Control of LLM Agents
Yuhan Ma, Stefan Schmid
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any fi…