{"total":25,"rows":[{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2311.00117","title":"BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2602.16703","title":"Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology","created":"2026-02-18","cited_by_count":6,"area":null},{"id":"2311.15936","title":"Towards Responsible Governance of Biological Design Tools","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2410.12104","title":"To Err is AI : A Case Study Informing LLM Flaw Reporting Practices","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2503.04299","title":"Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2501.06137","title":"Supervision policies can shape long-term risk management in general-purpose AI models","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2608.02684","title":"A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2505.17154","title":"Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2605.21545","title":"RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2607.12200","title":"A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.02168","title":"FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.16213","title":"Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}