{"total":337,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"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":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486,"area":"safety"},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451,"area":"safety"},{"id":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385,"area":"safety"},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"area":"safety"},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230,"area":"safety"},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216,"area":"safety"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"area":"safety"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167,"area":"safety"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156,"area":"safety"},{"id":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145,"area":"safety"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118,"area":"safety"},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110,"area":"safety"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2402.13494","title":"GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis","created":"2024-02-21","cited_by_count":96,"area":"safety"},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89,"area":"safety"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"id":"2406.13356","title":"Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning","created":"2024-06-19","cited_by_count":84,"area":"safety"},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2402.16717","title":"CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models","created":"2024-02-26","cited_by_count":76,"area":"safety"},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76,"area":"safety"},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"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":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"area":"safety"},{"id":"2402.16459","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","created":"2024-02-26","cited_by_count":70,"area":"safety"},{"id":"2406.01288","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","created":"2024-06-03","cited_by_count":70,"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":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68,"area":"safety"},{"id":"2402.17262","title":"Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue","created":"2024-02-27","cited_by_count":66,"area":"safety"},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2408.04686","title":"Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles","created":"2024-08-08","cited_by_count":56,"area":"safety"},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55,"area":"safety"},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54,"area":"safety"},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"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":"2406.09324","title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","created":"2024-06-13","cited_by_count":51,"area":"safety"},{"id":"2312.12321","title":"Bypassing the Safety Training of Open-Source LLMs with Priming Attacks","created":"2023-12-19","cited_by_count":50,"area":"safety"},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"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":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2405.01229","title":"Boosting Jailbreak Attack with Momentum","created":"2024-05-02","cited_by_count":40,"area":"safety"},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39,"area":"safety"},{"id":"2403.01251","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","created":"2024-03-02","cited_by_count":37,"area":"safety"},{"id":"2406.09289","title":"Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models","created":"2024-06-13","cited_by_count":37,"area":"safety"},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2410.18210","title":"Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks","created":"2024-10-23","cited_by_count":33,"area":"safety"},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30,"area":"safety"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2406.11614","title":"Intrinsic Test of Unlearning Using Parametric Knowledge Traces","created":"2024-06-17","cited_by_count":29,"area":"safety"},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2401.09002","title":"AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models","created":"2024-01-17","cited_by_count":28,"area":"safety"},{"id":"2503.16431","title":"OpenAI's Approach to External Red Teaming for AI Models and Systems","created":"2025-01-24","cited_by_count":28,"area":"safety"},{"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":"2506.17209","title":"Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency","created":"2025-06-20","cited_by_count":27,"area":"safety"},{"id":"2604.09378","title":"BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning","created":"2026-04-10","cited_by_count":27,"area":"safety"},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24,"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":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"area":"safety"},{"id":"2411.01077","title":"Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection","created":"2024-11-01","cited_by_count":23,"area":"safety"},{"id":"2407.20224","title":"Can Editing LLMs Inject Harm?","created":"2024-07-29","cited_by_count":22,"area":"safety"},{"id":"2502.03052","title":"Understanding and Enhancing the Transferability of Jailbreaking Attacks","created":"2025-02-05","cited_by_count":22,"area":"safety"},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"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":"2411.08410","title":"The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense","created":"2024-11-13","cited_by_count":21,"area":"safety"},{"id":"2506.01339","title":"Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning","created":"2025-06-02","cited_by_count":21,"area":"safety"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2402.14857","title":"Is the System Message Really Important to Jailbreaks in Large Language Models?","created":"2024-02-20","cited_by_count":20,"area":"safety"},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2407.00869","title":"Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks","created":"2024-07-01","cited_by_count":19,"area":"safety"},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2506.07596","title":"TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts","created":"2025-06-09","cited_by_count":19,"area":"safety"},{"id":"2405.04160","title":"A Causal Explainable Guardrails for Large Language Models","created":"2024-05-07","cited_by_count":18,"area":"safety"},{"id":"2406.11780","title":"Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs","created":"2024-06-17","cited_by_count":18,"area":"safety"},{"id":"2501.09798","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","created":"2025-01-16","cited_by_count":17,"area":"safety"},{"id":"2408.11006","title":"Security Attacks on LLM-based Code Completion Tools","created":"2024-08-20","cited_by_count":16,"area":"safety"},{"id":"2410.02163","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2502.13141","title":"UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models","created":"2025-02-18","cited_by_count":16,"area":"safety"},{"id":"2505.17568","title":"JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models","created":"2025-05-23","cited_by_count":16,"area":"safety"},{"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":"2509.24384","title":"HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment","created":"2025-09-29","cited_by_count":15,"area":"safety"}],"next_cursor":"100"}