Cover Image

AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhan, Zhonghao, Sadi, Amir Al, Li, Krinos, Haddadi, Hamed
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Systems-Level Attack Surface of Edge Agent Deployments on IoT
by: Zhan, Zhonghao, et al.
Published: (2026)

HearthNet: Edge Multi-Agent Orchestration for Smart Homes
by: Zhan, Zhonghao, et al.
Published: (2026)

REAL-IoT: Characterizing GNN Intrusion Detection Robustness under Practical Adversarial Attack
by: Zhan, Zhonghao, et al.
Published: (2025)

Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis
by: Zhan, Zhonghao, et al.
Published: (2025)

AgenTEE: Confidential LLM Agent Execution on Edge Devices
by: Abdollahi, Sina, et al.
Published: (2026)

CAEC: Confidential, Attestable, and Efficient Inter-CVM Communication with Arm CCA
by: Abdollahi, Sina, et al.
Published: (2025)

Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components
by: Sadi, Amir Al, et al.
Published: (2026)

Verifiable Unlearning on Edge
by: Maheri, Mohammad M, et al.
Published: (2025)

Dynamic Probabilistic Noise Injection for Membership Inference Defense
by: Forough, Javad, et al.
Published: (2025)

Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
by: Trong, Thua Huynh, et al.
Published: (2024)

Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices
by: Ieropoulos, Vasilis, et al.
Published: (2026)

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
by: Li, Ruiqi, et al.
Published: (2026)

Unbundle-Rewrite-Rebundle: Runtime Detection and Rewriting of Privacy-Harming Code in JavaScript Bundles
by: Ali, Mir Masood, et al.
Published: (2024)

An Early Experience with Confidential Computing Architecture for On-Device Model Protection
by: Abdollahi, Sina, et al.
Published: (2025)

No Data? No Problem: Synthesizing Security Graphs for Better Intrusion Detection
by: Huang, Yi, et al.
Published: (2025)

TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection
by: Liu, Jiahao, et al.
Published: (2025)

Toward an Intrusion Detection System for a Virtualization Framework in Edge Computing
by: de Matos, Everton, et al.
Published: (2025)

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
by: Mohammad, Noor Islam S.
Published: (2026)

MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks
by: Hao, Run, et al.
Published: (2026)

Entente: Cross-silo Intrusion Detection on Network Log Graphs with Federated Learning
by: Xu, Jiacen, et al.
Published: (2025)

Think Fast: Real-Time IoT Intrusion Reasoning Using IDS and LLMs at the Edge Gateway
by: Jamshidi, Saeid, et al.
Published: (2025)

AOC-IDS: Autonomous Online Framework with Contrastive Learning for Intrusion Detection
by: Zhang, Xinchen, et al.
Published: (2024)

Web Execution Bundles: Reproducible, Accurate, and Archivable Web Measurements
by: Hantke, Florian, et al.
Published: (2025)

The Boomerang protocol: A Decentralised Privacy-Preserving Verifiable Incentive Protocol
by: Ankele, Ralph, et al.
Published: (2023)

AegisSat: Securing AI-Enabled SoC FPGA Satellite Platforms
by: Li, Huimin, et al.
Published: (2026)

SoK: Harmonizing Attack Graphs and Intrusion Detection Systems
by: Agiollo, Andrea, et al.
Published: (2026)

Machine Learning with Confidential Computing: A Systematization of Knowledge
by: Mo, Fan, et al.
Published: (2022)

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
by: Forough, Javad, et al.
Published: (2026)

Local Frames: Exploiting Inherited Origins to Bypass Content Blockers
by: Ukani, Alisha, et al.
Published: (2025)

Privacy Practices of Browser Agents
by: Ukani, Alisha, et al.
Published: (2025)

MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools
by: Tan, Zhuoran, et al.
Published: (2026)

GraphFaaS: Serverless GNN Inference for Burst-Resilient, Real-Time Intrusion Detection
by: Wang, Lingzhi, et al.
Published: (2025)

An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection
by: Fard, Hamed, et al.
Published: (2025)

SoK: Analysis of Privacy Risks and Mitigation in Online Propaganda Detection through the PROMPT Framework
by: Goswami, Dhiman, et al.
Published: (2026)

A Robust Multi-Stage Intrusion Detection System for In-Vehicle Network Security using Hierarchical Federated Learning
by: Althunayyan, Muzun, et al.
Published: (2024)

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents
by: Li, Xiang, et al.
Published: (2026)

Optimising Intrusion Detection Systems in Cloud-Edge Continuum with Knowledge Distillation for Privacy-Preserving and Efficient Communication
by: Almabdy, Soad, et al.
Published: (2025)

GuaranTEE: Towards Attestable and Private ML with CCA
by: Siby, Sandra, et al.
Published: (2024)

Optimizing IoT Intrusion Detection with Tabular Foundation Models for Smart City Forensics
by: Al-Dahmani, Asma, et al.
Published: (2026)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
by: Wang, Yihan, et al.
Published: (2025)