{"total":25,"rows":[{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83,"area":"safety"},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2601.11516","title":"Building Production-Ready Probes For Gemini","created":"2026-01-16","cited_by_count":47,"area":"safety"},{"id":"2409.07985","title":"Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols","created":"2024-09-12","cited_by_count":31,"area":"safety"},{"id":"2411.17693","title":"Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats","created":"2024-11-26","cited_by_count":31,"area":"safety"},{"id":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25,"area":"safety"},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23,"area":"safety"},{"id":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"safety"},{"id":"2511.02997","title":"Evaluating Control Protocols for Untrusted AI Agents","created":"2025-11-04","cited_by_count":11,"area":"safety"},{"id":"2410.09097","title":"Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations","created":"2024-10-09","cited_by_count":8,"area":"safety"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2602.04930","title":"Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring","created":"2026-02-04","cited_by_count":6,"area":"safety"},{"id":"2606.12747","title":"Prefill Awareness in Large Language Models","created":"2026-06-10","cited_by_count":4,"area":"safety"},{"id":"2507.03010","title":"Subversion via Focal Points: Investigating Collusion in LLM Monitoring","created":"2025-07-02","cited_by_count":3,"area":"safety"},{"id":"2602.10153","title":"Basic Legibility Protocols Improve Trusted Monitoring","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2506.05376","title":"A Red Teaming Roadmap Towards System-Level Safety","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2508.06755","title":"Many-Turn Jailbreaking","created":"2025-08-09","cited_by_count":2,"area":"safety"},{"id":"2507.06282","title":"The bitter lesson of misuse detection","created":"2025-07-08","cited_by_count":0,"area":"safety"},{"id":"2512.03089","title":"Password-Activated Shutdown Protocols for Misaligned Frontier Agents","created":"2025-11-29","cited_by_count":0,"area":"safety"},{"id":"2602.08877","title":"Stress-Testing Alignment Audits With Prompt-Level Strategic Deception","created":"2026-02-09","cited_by_count":0,"area":"safety"},{"id":"2606.08892","title":"Diffuse AI Control on Fuzzy Tasks","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2607.20852","title":"Code Monitor Red Teaming for Public-Test-Passing Code","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2609.06966","title":"MOLE: Detecting Insider Threats in AI Agents","created":"2026-09-07","cited_by_count":0,"area":"safety"},{"id":"2609.30217","title":"Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure","created":"2026-09-24","cited_by_count":0,"area":"safety"}],"next_cursor":null}