{"total":20,"rows":[{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032,"area":"safety"},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605,"area":"safety"},{"id":"2311.03348","title":"Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation","created":"2023-11-06","cited_by_count":214,"area":"safety"},{"id":"2507.06908","title":"MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection","created":"2025-07-09","cited_by_count":15,"area":"safety"},{"id":"2410.03857","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2602.13284","title":"Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook","created":"2026-02-07","cited_by_count":10,"area":"safety"},{"id":"2406.07188","title":"Merging Improves Self-Critique Against Jailbreak Attacks","created":"2024-06-11","cited_by_count":8,"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":"2508.09762","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":"2509.00391","title":"The Resurgence of GCG Adversarial Attacks on Large Language Models","created":"2025-08-30","cited_by_count":3,"area":"safety"},{"id":"2511.11020","title":"Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis","created":"2025-11-14","cited_by_count":3,"area":"safety"},{"id":"2506.04975","title":"Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"id":"2601.03134","title":"The Anatomy of Conversational Scams: A Topic-Based Red Teaming Analysis of Multi-Turn Interactions in LLMs","created":"2026-01-06","cited_by_count":2,"area":"safety"},{"id":"2511.23174","title":"Are LLMs Good Safety Agents or a Propaganda Engine?","created":"2025-11-28","cited_by_count":0,"area":"safety"},{"id":"2604.17020","title":"Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation","created":"2026-04-18","cited_by_count":0,"area":"safety"},{"id":"2605.01758","title":"Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems","created":"2026-05-03","cited_by_count":0,"area":"safety"},{"id":"2605.05682","title":"PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2606.00654","title":"The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction","created":"2026-05-30","cited_by_count":0,"area":"safety"},{"id":"2606.26377","title":"Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2608.06416","title":"WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking","created":"2026-08-05","cited_by_count":0,"area":"safety"}],"next_cursor":null}