Overview

AI agent security studies how tool use, memory, delegation, and interaction with people or environments create risks beyond those of a standalone language model, including prompt injection, privilege misuse, data leakage, and unsafe actions. Researchers test these risks with red-teaming and execution-grounded benchmarks for coding, browsing, GUI, embodied, and multi-agent tasks, measuring whether harmful effects occur across trajectories rather than judging text alone. Defenses range from input and memory provenance checks to sandboxing, least-privilege permissions, stateful runtime authorization, action verification, and cryptographic identity or audit mechanisms. An open challenge is making controls robust to adaptive, long-horizon attacks and interactions between tools or agents while preserving useful task completion; benchmark realism and comparable measures remain uneven.

Latest papers

CardsList

563 papers61 papers in the last four weeks, down 18% on the four weeks before. 0.5% of all new papers.

  1. Replication of Agentic Security Events: Audit and Investigation (ROGUE-AI)

    Nov 19, 2026Mengxiao Wang, Mahbub Alam, Kalyan Nakka +1AI Agent SecurityAI Agent Auditing

  2. Backtracking Agent Applications Security Incidents

    Nov 19, 2026Yicheng Cai, Taegyu Kim, Peng LiuAI Agent SecurityAI Agent Auditing

  3. Tether: Verified Stateful Policy Engine for System-Level Monitoring of Agents

    Nov 19, 2026Meghana Aparna Sistla, Alaia Solko-Breslin, Somesh Jha +2AI Agent SecurityRuntime Enforcement for AI Agents

  4. A Synthetic Multi-Modal Testbed for Security Stress Testing of Agentic Counter-UAS Systems

    Nov 18, 2026Ivan A. Fernandez, Jingdao ChenAI Agent Security

  5. IDEA: Intent-Dominance Evidence Audit for Inference-Time Backdoor Detection in GUI Agents

    Nov 18, 2026Zhizhuo Kou, Sizai Hou, Jian Yang +5Backdoor DetectionAI Agent Security

  6. Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

    Nov 17, 2026Stanley Akingbola, Ugbede Ibrahim, Yan Lin Aung +2CybersecurityAI Agent Security

  7. Evolution Under Fire: Evolving Agent Safety Harnesses with Adaptive Injection Stressors

    Nov 17, 2026Yujun Wang, Yilun Liu, Jinhe Bi +4AI Agent SecurityAgent Harness Self-Evolution

  8. ConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agents

    Nov 17, 2026Arunkumar V, Gangadharan G. R., S. SenthilkumarAI Agent SecurityAI Agent Monitoring

  9. Evaluating Authorization and Trust Boundaries in Agentic Orchestration Frameworks

    Nov 16, 2026Sahaya Jestus Lazer, Kshitiz Aryal, Maanak Gupta +1AI Agent SecurityTool Access Control for LLM Agents

  10. Hardening Agentic Web Populations Through Multi-Criterion Competitive Co-Evolution: Lessons from Wargame Strategy Optimization

    Nov 14, 2026Shashank Raj, Kalyanmoy DebAI Agent SecurityAdversarial Attacks on LLMs

  11. We Have All the Cards: Securing Agent Cards at the Operational Trust Boundary of the Agent2Agent Protocol

    Nov 13, 2026Miguel A. Guirao Aguilera, Satyajayant Misra, Efren Lopez-MoralesAI Agent SecurityAI Agent Interoperability

  12. Bait: Mitigating Harmful Agentic Reinforcement Learning via Probing Reward Function

    Nov 12, 2026Tiansheng Huang, Ananth Balashankar, Virat Shejwalkar +2AI Agent SecurityLLM Agent Safety

  13. Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

    Nov 11, 2026Yuchen Zeng, Giorgio Severi, Blake Bullwinkel +2LLM Backdoor AttacksAI Agent Security

  14. From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

    Nov 10, 2026Simon Hegelich, Bardh Prenkaj, Habiba Sarhan +5AI Agent SecurityTool Access Control for LLM Agents

  15. Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks

    Nov 9, 2026Dario Pasquini, Reworr, Giuseppe Ateniese +2Language Model FingerprintingAI Agent Security

  16. The Limits of Information-Flow Control Enforcement for Agentic Systems

    Nov 7, 2026Jonathan Gregory, Kyle Domico, Kunyang Li +2Information Flow ControlAI Agent Security

  17. AI Governance Should Prioritize Control and Knowledge Boundaries Over Limiting Intelligence

    Nov 6, 2026Hendrik LuukAI Agent GovernanceAI Control

  18. Toward Safety-Aware AI Agents in Realistic Social Engineering Attack Scenarios

    Nov 5, 2026Zhitao He, Chengru Han, Chi Him Zhang +1AI Agent SecurityAI Agent Security Benchmarks

  19. Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks

    Nov 5, 2026Zhitao He, Chi Him Zhang, Chengru Han +1AI Agent SecurityAI Agent Security Benchmarks

  20. Authorization Propagation in Agent2Agent Systems: An Experimental Security Evaluation of Multi-Hop Delegation

    Nov 4, 2026Gabriele Donno, Kashif Mehmood, Katina KralevskaMulti-Agent System SecurityAI Agent Security

  21. Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity

    Nov 4, 2026Ahsan Habib Shihab, Imre Felde, Ramis Akhmedov +4Runtime Enforcement for AI AgentsAccess Control

  22. SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents

    Nov 4, 2026Guoqin Xiong, Shengtao Wen, Xiang Chen +5AI Agent SecurityTool Access Control for LLM Agents