{"total":452,"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":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"area":"safety"},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"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":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"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":"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":"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":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156,"area":"safety"},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"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":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113,"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":"2402.18104","title":"Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction","created":"2024-02-28","cited_by_count":107,"area":"safety"},{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"area":"safety"},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98,"area":"safety"},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","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":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79,"area":"safety"},{"id":"2502.05374","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","created":"2025-02-07","cited_by_count":79,"area":"safety"},{"id":"2406.10890","title":"RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models","created":"2024-06-16","cited_by_count":78,"area":"safety"},{"id":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75,"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":"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":"2410.18927","title":"SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models","created":"2024-10-24","cited_by_count":69,"area":"safety"},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67,"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":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64,"area":"safety"},{"id":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"area":"safety"},{"id":"2410.21965","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","created":"2024-10-29","cited_by_count":60,"area":"safety"},{"id":"2410.08109","title":"A Closer Look at Machine Unlearning for Large Language Models","created":"2024-10-10","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":"2502.19820","title":"Foot-In-The-Door: A Multi-turn Jailbreak for LLMs","created":"2025-02-27","cited_by_count":54,"area":"safety"},{"id":"2402.15911","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","created":"2024-02-24","cited_by_count":52,"area":"safety"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"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":"2406.15518","title":"Steering Without Side Effects: Improving Post-Deployment Control of Language Models","created":"2024-06-21","cited_by_count":46,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45,"area":"safety"},{"id":"2405.20413","title":"Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters","created":"2024-05-30","cited_by_count":42,"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":"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":"2410.18057","title":"CLEAR: Character Unlearning in Textual and Visual Modalities","created":"2024-10-23","cited_by_count":39,"area":"safety"},{"id":"2505.11953","title":"Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning","created":"2025-05-17","cited_by_count":39,"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":"2402.12991","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","created":"2024-02-20","cited_by_count":36,"area":"safety"},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"id":"2505.18333","title":"A Critical Evaluation of Defenses against Prompt Injection Attacks","created":"2025-05-23","cited_by_count":36,"area":"safety"},{"id":"2405.07932","title":"PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition","created":"2024-05-13","cited_by_count":35,"area":"safety"},{"id":"2503.07885","title":"Safety Guardrails for LLM-Enabled Robots","created":"2025-03-10","cited_by_count":35,"area":"safety"},{"id":"2401.16656","title":"Gradient-Based Language Model Red Teaming","created":"2024-01-30","cited_by_count":34,"area":"safety"},{"id":"2503.01854","title":"A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models","created":"2025-02-22","cited_by_count":34,"area":"safety"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"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":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"id":"2410.22086","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","created":"2024-10-29","cited_by_count":31,"area":"safety"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2402.15180","title":"Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement","created":"2024-02-23","cited_by_count":29,"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":"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":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28,"area":"safety"},{"id":"2406.09179","title":"Towards Effective Evaluations and Comparisons for LLM Unlearning Methods","created":"2024-06-13","cited_by_count":27,"area":"safety"},{"id":"2410.06606","title":"Dissecting Fine-Tuning Unlearning in Large Language Models","created":"2024-10-09","cited_by_count":26,"area":"safety"},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2409.16783","title":"Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction","created":"2024-09-25","cited_by_count":25,"area":"safety"},{"id":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"area":"safety"},{"id":"2310.14303","title":"Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases","created":"2023-10-22","cited_by_count":24,"area":"safety"},{"id":"2407.10058","title":"Learning to Refuse: Towards Mitigating Privacy Risks in LLMs","created":"2024-07-14","cited_by_count":23,"area":"safety"},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2403.10553","title":"Learning to Watermark LLM-generated Text via Reinforcement Learning","created":"2024-03-13","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":"2502.11190","title":"ReLearn: Unlearning via Learning for Large Language Models","created":"2025-02-16","cited_by_count":22,"area":"safety"},{"id":"2504.08192","title":"SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs","created":"2025-04-11","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":"2406.01983","title":"RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models","created":"2024-06-04","cited_by_count":21,"area":"safety"},{"id":"2410.14827","title":"Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment","created":"2024-10-18","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":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2510.14005","title":"PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features","created":"2025-10-15","cited_by_count":20,"area":"safety"},{"id":"2410.16531","title":"Bayesian scaling laws for in-context learning","created":"2024-10-21","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":"2503.04636","title":"Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking","created":"2025-03-06","cited_by_count":19,"area":"safety"},{"id":"2509.09708","title":"Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal","created":"2025-09-07","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":"2407.02551","title":"Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses","created":"2024-07-02","cited_by_count":18,"area":"safety"},{"id":"2409.11844","title":"MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts","created":"2024-09-18","cited_by_count":18,"area":"safety"},{"id":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"id":"2508.07173","title":"Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models","created":"2025-08-10","cited_by_count":18,"area":"safety"},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","cited_by_count":17,"area":"safety"}],"next_cursor":"100"}