Confidential Computing
3 resourcesPrivacy
TEEs, secure enclaves, and hardware-based AI privacy
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
Javad 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 sensitive context, hold credentials, and operate across pipelines no single party fully controls, enabling prompt injection, context exfiltration, credential theft, and inter-agent message poisoning. Current defenses operate
Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly
Herbert Woisetschlager, Alexander Isenko, Shiqiang Wang + 2 more — arXiv preprint
Examines federated learning approaches for fine-tuning LLMs on edge devices, analyzing privacy guarantees, communication efficiency, and security trade-offs.
Confidential Computing for AI Workloads: Survey and Best Practices
Microsoft Azure Confidential Computing Team — Microsoft Research
Surveys confidential computing technologies (SGX, SEV, TDX) applied to AI workloads covering secure training, inference, and multi-party computation.