{"total":48,"rows":[{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672,"area":"safety"},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560,"area":"safety"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469,"area":"safety"},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"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":"2311.09096","title":"Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization","created":"2023-11-15","cited_by_count":170,"area":"safety"},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76,"area":"safety"},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2307.08487","title":"Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models","created":"2023-07-17","cited_by_count":60,"area":"safety"},{"id":"2404.05880","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","created":"2024-04-08","cited_by_count":51,"area":"safety"},{"id":"2307.13808","title":"Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy","created":"2023-07-25","cited_by_count":50,"area":"safety"},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2401.09798","title":"All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks","created":"2024-01-18","cited_by_count":32,"area":"safety"},{"id":"2311.09433","title":"Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment","created":"2023-11-15","cited_by_count":30,"area":"safety"},{"id":"2407.02855","title":"From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks","created":"2024-07-03","cited_by_count":29,"area":"safety"},{"id":"2410.19937","title":"RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction","created":"2024-10-25","cited_by_count":21,"area":"safety"},{"id":"2505.05190","title":"Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks","created":"2025-05-08","cited_by_count":18,"area":"safety"},{"id":"2503.01865","title":"Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints","created":"2025-02-25","cited_by_count":11,"area":"safety"},{"id":"2501.12210","title":"You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense","created":"2025-01-21","cited_by_count":10,"area":"safety"},{"id":"2505.02862","title":"Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs","created":"2025-05-03","cited_by_count":9,"area":"safety"},{"id":"2406.07188","title":"Merging Improves Self-Critique Against Jailbreak Attacks","created":"2024-06-11","cited_by_count":8,"area":"safety"},{"id":"2408.10722","title":"MEGen: Generative Backdoor into Large Language Models via Model Editing","created":"2024-08-20","cited_by_count":8,"area":"safety"},{"id":"2409.07503","title":"AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs","created":"2024-09-11","cited_by_count":8,"area":"safety"},{"id":"2504.19674","title":"SAGE: A Generic Framework for LLM Safety Evaluation","created":"2025-04-28","cited_by_count":8,"area":"safety"},{"id":"2505.19773","title":"What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs","created":"2025-05-26","cited_by_count":8,"area":"safety"},{"id":"2502.11242","title":"LLMs and Childhood Safety: Identifying Risks and Proposing a Protection Framework for Safe Child-LLM Interaction","created":"2025-02-16","cited_by_count":7,"area":"safety"},{"id":"2506.13510","title":"Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions","created":"2025-06-16","cited_by_count":7,"area":"safety"},{"id":"2507.21820","title":"Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is","created":"2025-07-29","cited_by_count":7,"area":"safety"},{"id":"2510.09871","title":"CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs","created":"2025-10-10","cited_by_count":5,"area":"safety"},{"id":"2601.23081","title":"Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures","created":"2026-01-30","cited_by_count":5,"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":"2503.06253","title":"MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming","created":"2025-03-08","cited_by_count":1,"area":"safety"},{"id":"2509.24488","title":"Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"safety"},{"id":"2510.18454","title":"Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models","created":"2025-10-21","cited_by_count":1,"area":"safety"},{"id":"2512.21236","title":"Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2502.05291","title":"Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet","created":"2025-02-07","cited_by_count":0,"area":"safety"},{"id":"2602.04196","title":"The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment","created":"2026-02-04","cited_by_count":0,"area":"safety"},{"id":"2606.25380","title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2608.03210","title":"ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization","created":"2026-08-04","cited_by_count":0,"area":"safety"},{"id":"2609.03781","title":"IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks","created":"2026-09-03","cited_by_count":0,"area":"safety"}],"next_cursor":null}