2 citations · 2 across the 11 of their papers we have counts for
12 papers
Safe Skill Retirement for Physical Agents
Zhonghao Zhan, Xiao Ma, Hamed Haddadi
Agent skills bundle procedural guidance with execution conditions governing authority, user consent, and live environment state. When model capabilities advance, maintainers prune…
Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical World
Zhonghao Zhan, Hamed Haddadi
Self-evolving Skill harnesses (AutoSkills, Hermes Agent) generate more advisory orchestration automatically; their reported gains are efficiency, not safety. This misses the actual…
SimVerity: When Does Simulated Agent Success Survive Physical Deployment?
Zhonghao Zhan, Yefan Zhang, Krinos Li +1
Simulated evaluation is widely used to benchmark AI agents, yet how much evidence a simulated pass provides about physical deployment has not been systematically quantified. We pre…
Poster: EdgeCitadel -- Hybrid NATS-MQTT Orchestration for Edge Multi-Agent Systems
Zhonghao Zhan, Yefan Zhang, Hamed Haddadi
Edge-resident AI agents increasingly span home servers, IoT hubs, laptops, and phones, yet their coordination stacks still assume cloud-style transports or a central relay. We pres…
HearthNet: Edge Multi-Agent Orchestration for Smart Homes
Zhonghao Zhan, Krinos Li, Yefan Zhang +1
Smart-home users increasingly want to control their homes in natural language rather than assemble rules, dashboards, and API integrations by hand. At the same time, real deploymen…
How Adversarial Environments Mislead Agentic AI?
Zhonghao Zhan, Huichi Zhou, Zhenhao Li +3
Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluation…
Systems-Level Attack Surface of Edge Agent Deployments on IoT
Zhonghao Zhan, Krinos Li, Yefan Zhang +1
Edge deployment of LLM agents on IoT hardware introduces attack surfaces absent from cloud-hosted orchestration. We present an empirical security analysis of three architectures (c…
AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices
Zhonghao Zhan, Amir Al Sadi, Krinos Li +1
In this work, we study security of Model Context Protocol (MCP) agent toolchains and their applications in smart homes. We introduce AegisMCP, a protocol-level intrusion detector.…
Large Language Models Meet Virtual Cell: A Survey
Krinos Li, Xianglu Xiao, Shenglong Deng +7
Large language models (LLMs) are transforming cellular biology by enabling the development of "virtual cells"--computational systems that represent, predict, and reason about cellu…
REAL-IoT: Characterizing GNN Intrusion Detection Robustness under Practical Adversarial Attack
Zhonghao Zhan, Huichi Zhou, Hamed Haddadi
Graph Neural Network (GNN)-based network intrusion detection systems (NIDS) are often evaluated on single datasets, limiting their ability to generalize under distribution drift. F…
Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis
Zhonghao Zhan, Huichi Zhou, Hamed Haddadi
Graph Neural Networks (GNNs) show great promise for Network Intrusion Detection Systems (NIDS), particularly in IoT environments, but suffer performance degradation due to distribu…
TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
Huichi Zhou, Kin-Hei Lee, Zhonghao Zhan +5
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tai…