{"total":145,"rows":[{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437,"area":"agents"},{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306,"area":"agents"},{"id":"2503.18813","title":"Defeating Prompt Injections by Design","created":"2025-03-24","cited_by_count":297,"area":"agents"},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"id":"2504.18575","title":"WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks","created":"2025-04-22","cited_by_count":157,"area":"agents"},{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151,"area":"lr"},{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129,"area":"safety"},{"id":"2503.00061","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","created":"2025-02-27","cited_by_count":125,"area":"agents"},{"id":"2504.13203","title":"X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents","created":"2025-04-15","cited_by_count":125,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2506.14866","title":"OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents","created":"2025-06-17","cited_by_count":111,"area":"agents"},{"id":"2412.16682","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents","created":"2024-12-21","cited_by_count":99,"area":"agents"},{"id":"2503.09648","title":"A Survey on Trustworthy LLM Agents: Threats and Countermeasures","created":"2025-03-12","cited_by_count":96,"area":"agents"},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90,"area":"agents"},{"id":"2506.08837","title":"Design Patterns for Securing LLM Agents against Prompt Injections","created":"2025-06-10","cited_by_count":73,"area":"agents"},{"id":"2601.10156","title":"ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback","created":"2026-01-15","cited_by_count":72,"area":"agents"},{"id":"2502.08966","title":"RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage","created":"2025-02-13","cited_by_count":69,"area":"agents"},{"id":"2508.14925","title":"MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers","created":"2025-08-19","cited_by_count":66,"area":"agents"},{"id":"2502.08745","title":"IHEval: Evaluating Language Models on Following the Instruction Hierarchy","created":"2025-02-12","cited_by_count":53,"area":null},{"id":"2410.17520","title":"MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control","created":"2024-10-23","cited_by_count":51,"area":"agents"},{"id":"2505.11717","title":"WebInject: Prompt Injection Attack to Web Agents","created":"2025-05-16","cited_by_count":51,"area":"agents"},{"id":"2502.08586","title":"Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks","created":"2025-02-12","cited_by_count":49,"area":"agents"},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42,"area":"lr"},{"id":"2510.15994","title":"MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents","created":"2025-10-14","cited_by_count":42,"area":"agents"},{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2603.10749","title":"AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations","created":"2026-03-11","cited_by_count":38,"area":"agents"},{"id":"2502.01822","title":"Firewalls to Secure Dynamic LLM Agentic Networks","created":"2025-02-03","cited_by_count":36,"area":"agents"},{"id":"2506.00618","title":"RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents","created":"2025-05-31","cited_by_count":35,"area":"mllm"},{"id":"2510.19207","title":"Defending Against Prompt Injection with DataFilter","created":"2025-10-22","cited_by_count":35,"area":"safety"},{"id":"2504.14064","title":"DoomArena: A framework for Testing AI Agents Against Evolving Security Threats","created":"2025-04-18","cited_by_count":32,"area":"agents"},{"id":"2604.04989","title":"SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement","created":"2026-04-05","cited_by_count":30,"area":"agents"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2502.20383","title":"Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis","created":"2025-02-27","cited_by_count":27,"area":"agents"},{"id":"2604.11790","title":"ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection","created":"2026-04-13","cited_by_count":27,"area":"agents"},{"id":"2506.01055","title":"Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution","created":"2025-06-01","cited_by_count":26,"area":"agents"},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2602.10127","title":"\"Humans welcome to observe\": A First Look at the Agent Social Network Moltbook","created":"2026-02-02","cited_by_count":26,"area":"agents"},{"id":"2602.11510","title":"AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems","created":"2026-02-12","cited_by_count":25,"area":"agents"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2505.10924","title":"A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?","created":"2025-05-16","cited_by_count":23,"area":"agents"},{"id":"2506.01616","title":"MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments","created":"2025-06-02","cited_by_count":23,"area":"agents"},{"id":"2503.01908","title":"UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning","created":"2025-02-28","cited_by_count":21,"area":"lr"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2511.17959","title":"Towards Automating Data Access Permissions in AI Agents","created":"2025-11-22","cited_by_count":21,"area":null},{"id":"2601.05755","title":"VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit","created":"2026-01-09","cited_by_count":17,"area":"agents"},{"id":"2412.18371","title":"Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents","created":"2024-12-24","cited_by_count":16,"area":"agents"},{"id":"2505.23559","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","created":"2025-05-29","cited_by_count":16,"area":"agents"},{"id":"2603.19469","title":"A Framework for Formalizing LLM Agent Security","created":"2026-03-19","cited_by_count":16,"area":"agents"},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2410.13919","title":"LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild","created":"2024-10-17","cited_by_count":12,"area":"agents"},{"id":"2506.15170","title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2506.17318","title":"Context manipulation attacks : Web agents are susceptible to corrupted memory","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2604.10577","title":"The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents","created":"2026-04-12","cited_by_count":12,"area":"agents"},{"id":"2601.12449","title":"AgenTRIM: Tool Risk Mitigation for Agentic AI","created":"2026-01-18","cited_by_count":11,"area":"agents"},{"id":"2604.15415","title":"HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?","created":"2026-04-16","cited_by_count":11,"area":"agents"},{"id":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2605.14271","title":"Auditing Agent Harness Safety","created":"2026-05-14","cited_by_count":11,"area":"agents"},{"id":"2605.20530","title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","created":"2026-05-19","cited_by_count":10,"area":"agents"},{"id":"2505.18907","title":"Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations","created":"2025-05-25","cited_by_count":9,"area":"safety"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2511.15203","title":"Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks","created":"2025-11-19","cited_by_count":9,"area":"agents"},{"id":"2512.00966","title":"Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis","created":"2025-11-30","cited_by_count":9,"area":"agents"},{"id":"2505.04799","title":"Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems","created":"2025-05-07","cited_by_count":8,"area":"agents"},{"id":"2509.25624","title":"STAC: When Innocent Tools Form Dangerous Chains for LLM Agents","created":"2025-09-30","cited_by_count":8,"area":"agents"},{"id":"2603.18096","title":"A Trace-Based Assurance Framework for Agentic AI Orchestration: Contracts, Testing, and Governance","created":"2026-03-18","cited_by_count":8,"area":"agents"},{"id":"2605.29801","title":"AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security","created":"2026-05-28","cited_by_count":8,"area":"agents"},{"id":"2505.15935","title":"MAPS: A Multilingual Benchmark for Agent Performance and Security","created":"2025-05-21","cited_by_count":7,"area":"agents"},{"id":"2510.03417","title":"NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks","created":"2025-10-03","cited_by_count":7,"area":"safety"},{"id":"2601.19202","title":"Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs","created":"2026-01-27","cited_by_count":7,"area":"lr"},{"id":"2410.13691","title":"Jailbreaking LLM-Controlled Robots","created":"2024-10-17","cited_by_count":6,"area":"safety"},{"id":"2505.17735","title":"SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator","created":"2025-05-23","cited_by_count":6,"area":"agents"},{"id":"2509.24240","title":"Takedown: How It's Done in Modern Coding Agent Exploits","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2604.01194","title":"AgentWatcher: A Rule-based Prompt Injection Monitor","created":"2026-04-01","cited_by_count":6,"area":"safety"},{"id":"2606.03024","title":"SkillGuard: A Permission-Centric Framework for Agent Skill Security","created":"2026-06-02","cited_by_count":6,"area":"agents"},{"id":"2606.14832","title":"PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2608.24777","title":"StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing","created":"2026-08-25","cited_by_count":6,"area":"agents"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2502.01241","title":"Peering Behind the Shield: Guardrail Identification in Large Language Models","created":"2025-02-03","cited_by_count":5,"area":"safety"},{"id":"2509.05755","title":"Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment","created":"2025-09-06","cited_by_count":5,"area":"agents"},{"id":"2510.07505","title":"PEAR: Planner-Executor Agent Robustness Benchmark","created":"2025-10-08","cited_by_count":5,"area":"agents"},{"id":"2510.26037","title":"SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2602.09433","title":"Autonomous Action Runtime Management(AARM):A System Specification for Securing AI-Driven Actions at Runtime","created":"2026-02-10","cited_by_count":5,"area":null},{"id":"2602.13597","title":"AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks","created":"2026-02-14","cited_by_count":5,"area":"safety"},{"id":"2605.02801","title":"Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces","created":"2026-05-04","cited_by_count":5,"area":"agents"},{"id":"2605.08442","title":"Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents","created":"2026-05-08","cited_by_count":5,"area":"agents"},{"id":"2606.30306","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","created":"2026-06-29","cited_by_count":5,"area":null},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2602.16943","title":"Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2603.11862","title":"You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2606.07054","title":"TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents","created":"2026-06-05","cited_by_count":3,"area":"lr"},{"id":"2606.26479","title":"Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents","created":"2026-06-25","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2608.21156","title":"Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence","created":"2026-08-21","cited_by_count":3,"area":"agents"},{"id":"2510.11851","title":"Deep Research Agents Brings Deeper Harm","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2510.23675","title":"QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents","created":"2025-10-27","cited_by_count":2,"area":"agents"},{"id":"2511.17671","title":"MURMUR: Using cross-user chatter to break collaborative language agents in groups","created":"2025-11-21","cited_by_count":2,"area":"agents"},{"id":"2602.16346","title":"Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents","created":"2026-02-18","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}