{"total":81,"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":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385,"area":"safety"},{"id":"2410.05295","title":"AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs","created":"2024-10-03","cited_by_count":199,"area":"safety"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2402.13457","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","created":"2024-02-21","cited_by_count":106,"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":"2401.11880","title":"PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety","created":"2024-01-22","cited_by_count":80,"area":"agents"},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48,"area":"safety"},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45,"area":"safety"},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2405.01229","title":"Boosting Jailbreak Attack with Momentum","created":"2024-05-02","cited_by_count":40,"area":"safety"},{"id":"2410.23861","title":"Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models","created":"2024-10-31","cited_by_count":37,"area":"mllm"},{"id":"2402.09177","title":"Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks","created":"2024-02-14","cited_by_count":36,"area":"safety"},{"id":"2507.11097","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","created":"2025-07-15","cited_by_count":34,"area":"inference"},{"id":"2402.15302","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","created":"2024-02-23","cited_by_count":27,"area":"safety"},{"id":"2406.14859","title":"From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking","created":"2024-06-21","cited_by_count":24,"area":"mllm"},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2404.07242","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","created":"2024-04-09","cited_by_count":20,"area":null},{"id":"2407.05216","title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","created":"2024-07-07","cited_by_count":19,"area":null},{"id":"2410.11459","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","created":"2024-10-15","cited_by_count":19,"area":"lr"},{"id":"2402.07658","title":"The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models","created":"2024-02-12","cited_by_count":18,"area":null},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"id":"2412.08615","title":"Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models","created":"2024-12-11","cited_by_count":15,"area":"safety"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"area":"lr"},{"id":"2410.11272","title":"Cognitive Overload Attack:Prompt Injection for Long Context","created":"2024-10-15","cited_by_count":13,"area":"safety"},{"id":"2503.04833","title":"E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models","created":"2025-03-05","cited_by_count":12,"area":"mllm"},{"id":"2503.17882","title":"Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2412.15289","title":"SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage","created":"2024-12-19","cited_by_count":11,"area":"alignment"},{"id":"2412.15623","title":"JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs","created":"2024-12-20","cited_by_count":11,"area":"alignment"},{"id":"2508.05087","title":"JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2503.19134","title":"MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2512.24143","title":"Activation Steering for Masked Diffusion Language Models","created":"2025-12-30","cited_by_count":9,"area":"diffusion"},{"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":"2504.04215","title":"Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability","created":"2025-04-05","cited_by_count":7,"area":"mechinterp"},{"id":"2510.01529","title":"Bypassing Prompt Guards in Production with Controlled-Release Prompting","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2508.03936","title":"ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants","created":"2025-08-05","cited_by_count":6,"area":"safety"},{"id":"2407.01461","title":"Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement","created":"2024-07-01","cited_by_count":5,"area":"safety"},{"id":"2405.15984","title":"Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning","created":"2024-05-24","cited_by_count":4,"area":"rag"},{"id":"2411.01565","title":"SQL Injection Jailbreak: A Structural Disaster of Large Language Models","created":"2024-11-03","cited_by_count":4,"area":"safety"},{"id":"2508.05625","title":"How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations","created":"2025-08-07","cited_by_count":4,"area":"mechinterp"},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2507.15613","title":"Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems","created":"2025-07-21","cited_by_count":3,"area":null},{"id":"2601.04448","title":"Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2407.13796","title":"Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models","created":"2024-07-16","cited_by_count":2,"area":"safety"},{"id":"2409.20385","title":"Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2412.18551","title":"Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2503.08990","title":"Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks","created":"2025-03-12","cited_by_count":2,"area":"safety"},{"id":"2504.09712","title":"The Structural Safety Generalization Problem","created":"2025-04-13","cited_by_count":2,"area":"safety"},{"id":"2506.12274","title":"InfoFlood: Jailbreaking Large Language Models with Information Overload","created":"2025-06-13","cited_by_count":2,"area":"safety"},{"id":"2507.22564","title":"Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs","created":"2025-07-30","cited_by_count":2,"area":"safety"},{"id":"2508.06755","title":"Many-Turn Jailbreaking","created":"2025-08-09","cited_by_count":2,"area":"safety"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2511.02356","title":"ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs","created":"2025-11-04","cited_by_count":1,"area":"alignment"},{"id":"2512.04124","title":"When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models","created":"2025-12-02","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":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2604.01444","title":"Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models","created":"2026-04-01","cited_by_count":1,"area":"safety"},{"id":"2605.18915","title":"DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs","created":"2026-05-18","cited_by_count":1,"area":"mllm"},{"id":"2605.30693","title":"Triaging Threats to Specialized Guardrails","created":"2026-05-29","cited_by_count":1,"area":"safety"},{"id":"2606.11425","title":"JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization","created":"2026-06-09","cited_by_count":1,"area":"safety"},{"id":"2503.02123","title":"TMIQ: Quantifying Test and Measurement Domain Intelligence in Large Language Models","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2603.01724","title":"GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.17884","title":"DebugLM: Learning Traceable Training Data Provenance for LLMs","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.22837","title":"Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.26351","title":"A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.25534","title":"StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2608.02681","title":"Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting","created":"2026-08-03","cited_by_count":0,"area":"safety"},{"id":"2608.09095","title":"Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.08634","title":"Suan: Rectifying Direct Preference Safety Alignment in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}