- [2025/05] LlamaFirewall: An open source guardrail system for building secure AI agents
- [2025/05] Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
- [2025/04] SAGA: A Security Architecture for Governing AI Agentic Systems
- [2025/04] RepliBench: Evaluating the autonomous replication capabilities of language model agents
- [2025/04] WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
- [2025/04] Prompt Injection Attack to Tool Selection in LLM Agents
- [2025/04] Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach
- [2025/04] Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents
- [2025/04] Simplified and Secure MCP Gateways for Enterprise AI Integration
- [2025/04] Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
- [2025/04] DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
- [2025/04] CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
- [2025/04] MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System
- [2025/04] Progent: Programmable Privilege Control for LLM Agents
- [2025/04] The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
- [2025/04] RealHarm: A Collection of Real-World Language Model Application Failures
- [2025/04] Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
- [2025/04] Detecting Malicious AI Agents Through Simulated Interactions
- [2025/04] MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
- [2025/03] Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- [2025/03] Get the Agents Drunk: Memory Perturbations in Autonomous Agent-based Recommender Systems
- [2025/03] ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- [2025/03] sudo rm -rf agentic_security
- [2025/03] Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
- [2025/02] DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
- [2025/02] "Nuclear Deployed!": Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
