most citedBlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability

1 citations · 1 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CR2026

Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection

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 com…

cs.CR2026

AgentKernel: The Trust-Native Agentic Operating System

Zhenhua Zou, Sheng Guo, Qiuyang Zhan +3

Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and inv…

cs.CR2026

InterSAGE: The Secure and Verifiable Interoperability Protocol for An Internet of Agents

Zhenhua Zou, Sheng Guo, Qiuyang Zhan +3

The emerging Internet of Agents enables LLM-powered agents to discover peers, invoke tools, and delegate tasks across organizational boundaries. Existing protocols increasingly def…

cs.AI2026

When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary

Qiuyang Zhan, Rui Zhang, Sheng Guo +2

Persistent memory allows (self-evolving) LLM agents to adapt across tasks by consolidating heterogeneous interaction histories into reusable facts, preferences, observations, and r…

cs.AI2026

TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI

Qi Li, Zhenhua Zou, Shuo Li +2

AI agents increasingly access external models, tools, and services through Agentic Routing Infrastructure (ARI) to manage the overhead of heterogeneous interfaces and fragmented su…

cs.CR2026

Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System

Zhenhua Zou, Sheng Guo, Qiuyang Zhan +6

The evolution of Large Language Models (LLMs) has shifted mobile computing from App-centric interactions to system-level autonomous agents. Current implementations predominantly re…