{"total":21,"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":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2410.01606","title":"Automated Red Teaming with GOAT: the Generative Offensive Agent Tester","created":"2024-10-02","cited_by_count":45,"area":"agents"},{"id":"2602.16901","title":"AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks","created":"2026-02-18","cited_by_count":39,"area":"agents"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2509.22830","title":"ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents","created":"2025-09-26","cited_by_count":31,"area":"agents"},{"id":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30,"area":"agents"},{"id":"2502.01236","title":"Eliciting Language Model Behaviors with Investigator Agents","created":"2025-02-03","cited_by_count":23,"area":"agents"},{"id":"2504.01278","title":"Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning","created":"2025-04-02","cited_by_count":8,"area":"agents"},{"id":"2512.14860","title":"Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks","created":"2025-12-16","cited_by_count":4,"area":"agents"},{"id":"2606.09084","title":"Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps","created":"2026-06-08","cited_by_count":2,"area":"agents"},{"id":"2607.18063","title":"Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2510.14207","title":"Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks","created":"2025-10-16","cited_by_count":1,"area":"agents"},{"id":"2606.14517","title":"From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails","created":"2026-06-12","cited_by_count":1,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2606.04141","title":"Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.07867","title":"The Cold-Start Safety Gap in LLM Agents","created":"2026-06-05","cited_by_count":0,"area":"agents"},{"id":"2606.13994","title":"Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2607.29199","title":"Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2609.27773","title":"Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2610.07089","title":"Towards a Unified Misuse Monitoring Benchmark","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}