TEEs, secure enclaves, and hardware-based AI privacy
Newest first · 1 reviewed on this page
Search insteadJavad Forough, Marios Kogias, Hamed Haddadi
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone model inference. Agents accumulate…
Hanyi Zhou, Chenyang Li, Yuanzhe Pang +3
Trusted Execution Environments (TEEs) offer a promising mechanism for safeguarding the intellectual property of on-device Large Language Models (LLMs). To overcome the inherent computational bottlenecks of TEEs, existing TEE-Shielded LLM Partition (TSLP) methods apply efficient…
Herbert Woisetschläger, Alexander Isenko, Shiqiang Wang +2
Examines federated learning approaches for fine-tuning LLMs on edge devices, analyzing privacy guarantees, communication efficiency, and security trade-offs.