mlsanityData to 14 Oct 2026

Security of Internet of Agents: Attacks and Countermeasures

arXiv 2505.08807 ↗First posted 12 May 2025cs.CR cs.AIcited by 17

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

With the rise of large language and vision-language models, AI agents have evolved into autonomous, interactive systems capable of perception, reasoning, and decision-making. As they proliferate across virtual and physical domains, the Internet of Agents (IoA) has emerged as a key infrastructure for enabling scalable and secure coordination among heterogeneous agents. This survey offers a comprehensive examination of the security and privacy landscape in IoA systems. We begin by outlining the IoA architecture and its distinct vulnerabilities compared to traditional networks, focusing on four critical aspects: identity authentication threats, cross-agent trust issues, embodied security, and privacy risks. We then review existing and emerging defense mechanisms and highlight persistent challenges. Finally, we identify open research directions to advance the development of resilient and privacy-preserving IoA ecosystems.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 40 of its 70 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

40 of 70 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment22 Apr
  2. 2025textitAgents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks31 Mar
  3. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents14 Nov
  4. 2024DAWN: Designing Distributed Agents in a Worldwide Network11 Oct
  5. 2024Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection12 Aug
  6. 2024Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification30 Jul
  7. 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies28 Jul
  8. 2024BadRobot: Jailbreaking Embodied LLM Agents in the Physical World16 Jul
  9. 2024GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning13 Jun
  10. 2024Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems27 May
  11. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks2 Mar
  12. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganography12 Feb

Other references · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Extracting Training Data from Large Language Modelscited by 2,189
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023How Language Model Hallucinations Can Snowballcited by 311
  6. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  7. 2023Certifying LLM Safety against Adversarial Promptingcited by 266
  8. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 265
  9. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  10. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  12. 2021Data Augmentation Can Improve Robustnesscited by 194
16 more
  1. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  2. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 186
  3. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Modelscited by 175
  4. 2023ProPILE: Probing Privacy Leakage in Large Language Modelscited by 129
  5. 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 128
  6. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  7. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 124
  8. 2024Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligencecited by 86
  9. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  10. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Datacited by 52
  11. 2021How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agentscited by 17
  12. 2024A Survey on Decentralized Identifiers and Verifiable Credentialscited by 11
  13. 2024Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigationcited by 7
  14. 2022Social-Aware Clustered Federated Learning with Customized Privacy Preservationcited by 5
  15. 2025Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaborationcited by 5
  16. 2025M2AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholdingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 9.

17 papers.

Sort:

By area:

  1. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 59
  2. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  3. 2025AgentBound: Securing Execution Boundaries of AI Agentscited by 23
  4. 2026Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANPcited by 15
  5. 2026From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaborationcited by 14
  6. 2025The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerabilitycited by 12
  7. 2025Toward a Safe Internet of Agentscited by 6
  8. 2026TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systemscited by 5
  9. 2025SoK: Security and Privacy of AI Agents for Blockchaincited by 4
  10. 2025Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agentscited by 3
  11. 2026Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharingcited by 1
  12. 2026Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffscited by 1
5 more
  1. 2026Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasurescited by 1
  2. 2026Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directionscited by 1
  3. 2025Hybrid Stackelberg Game and Diffusion-based Auction for Two-tier Agentic AI Task Offloading in Internet of Agentscited by 0
  4. 2026SS-ZKR: Spatial-Semantic Zero-Knowledge Routing for Privacy-Preserving Multi-Agent Collaborationcited by 0
  5. 2026TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Serverscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Internet of Agents: Fundamentals, Applications, and Challenges
  2. 2026The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale
  3. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
  4. 2026The Internet of Physical AI Agents: Interoperability, Longevity, and the Cost of Getting It Wrong
  5. 2026Rethinking Agent Security as a Networking Problem
  6. 2026The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey
  7. 2025BlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability
  8. 2025A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control