{"total":16,"rows":[{"id":"2505.11413","title":"CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs","created":"2025-05-16","cited_by_count":26,"area":"safety"},{"id":"2506.14922","title":"FORTRESS: Frontier Risk Evaluation for National Security and Public Safety","created":"2025-06-17","cited_by_count":24,"area":"safety"},{"id":"2602.22983","title":"Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search","created":"2026-02-26","cited_by_count":13,"area":"safety"},{"id":"2505.14368","title":"From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2508.04196","title":"Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models","created":"2025-08-06","cited_by_count":4,"area":"safety"},{"id":"2508.09762","title":"The PacifAIst Benchmark:Would an Artificial Intelligence Choose to Sacrifice Itself for Human Safety?","created":"2025-08-13","cited_by_count":4,"area":"safety"},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2602.20170","title":"CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2604.18487","title":"Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety","created":"2026-04-20","cited_by_count":3,"area":"safety"},{"id":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"id":"2510.08329","title":"AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming","created":"2025-10-09","cited_by_count":1,"area":"safety"},{"id":"2602.11786","title":"Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2603.10807","title":"Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services","created":"2026-03-11","cited_by_count":1,"area":"safety"},{"id":"2606.19887","title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2608.02665","title":"Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity","created":"2026-08-01","cited_by_count":1,"area":"safety"},{"id":"2610.02827","title":"MLCommons Jailbreak Benchmark v1.0","created":"2026-10-02","cited_by_count":0,"area":"safety"}],"next_cursor":null}