5 papers · 1 filter
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, introdu…
AgenTEE: Confidential LLM Agent Execution on Edge Devices
Sina Abdollahi, Mohammad M Maheri, Javad Forough +5
Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their t…
Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components
Amir Al Sadi, Sina Abdollahi, Adrien Ghosn +2
Trusted Execution Environments (TEEs) protect private memory and attest initial code and configuration, but neither constrain nor attest shared channels between TEEs or with the un…
CAEC: Confidential, Attestable, and Efficient Inter-CVM Communication with Arm CCA
Sina Abdollahi, Amir Al Sadi, David Kotz +2
Confidential Virtual Machines (CVMs) are increasingly adopted to protect sensitive workloads from privileged adversaries such as the hypervisor. While they provide strong isolation…
An Early Experience with Confidential Computing Architecture for On-Device Model Protection
Sina Abdollahi, Mohammad Maheri, Sandra Siby +2
Deploying machine learning (ML) models on user devices can improve privacy (by keeping data local) and reduce inference latency. Trusted Execution Environments (TEEs) are a practic…