{"total":355,"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":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"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":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385,"area":"safety"},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"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":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223,"area":"safety"},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205,"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":"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":"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":"2408.00761","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":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"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":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","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":"2506.12618","title":"OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics","created":"2025-06-14","cited_by_count":83,"area":"safety"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"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":"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":"2403.00867","title":"Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","created":"2024-03-01","cited_by_count":74,"area":"safety"},{"id":"2310.07676","title":"Composite Backdoor Attacks Against Large Language Models","created":"2023-10-11","cited_by_count":73,"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":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71,"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":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"area":"safety"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"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":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54,"area":"safety"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"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":"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":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"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":"2403.01267","title":"Dissecting Language Models: Machine Unlearning via Selective Pruning","created":"2024-03-02","cited_by_count":42,"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":"2505.11953","title":"Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning","created":"2025-05-17","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":"2506.09443","title":"LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge","created":"2025-06-11","cited_by_count":37,"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":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35,"area":"safety"},{"id":"2406.15481","title":"Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding","created":"2024-06-17","cited_by_count":34,"area":"safety"},{"id":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33,"area":"safety"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2402.13148","title":"Defending Jailbreak Prompts via In-Context Adversarial Game","created":"2024-02-20","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":"2411.03343","title":"What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks","created":"2024-11-02","cited_by_count":29,"area":"safety"},{"id":"2404.06664","title":"CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge","created":"2024-04-10","cited_by_count":28,"area":"safety"},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2504.10694","title":"The Jailbreak Tax: How Useful are Your Jailbreak Outputs?","created":"2025-04-14","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":"2406.16257","title":"Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning","created":"2024-06-24","cited_by_count":27,"area":"safety"},{"id":"2401.10862","title":"Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning","created":"2024-01-19","cited_by_count":26,"area":"safety"},{"id":"2407.01920","title":"To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models","created":"2024-07-02","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":"2411.12103","title":"Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods","created":"2024-11-18","cited_by_count":26,"area":"safety"},{"id":"2409.07314","title":"MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical Applications","created":"2024-09-11","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":"2406.10952","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","created":"2024-06-16","cited_by_count":24,"area":"safety"},{"id":"2502.15097","title":"LUME: LLM Unlearning with Multitask Evaluations","created":"2025-02-20","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":"2402.14883","title":"Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning","created":"2024-02-22","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":"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":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","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":"2510.14005","title":"PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features","created":"2025-10-15","cited_by_count":20,"area":"safety"},{"id":"2410.01294","title":"Endless Jailbreaks with Bijection Learning","created":"2024-10-02","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":"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":"2505.24428","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections","created":"2025-05-30","cited_by_count":18,"area":"safety"},{"id":"2409.14729","title":"PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs","created":"2024-09-23","cited_by_count":17,"area":"safety"},{"id":"2507.09709","title":"Large Language Models Encode Semantics and Alignment in Linearly Separable Representations","created":"2025-07-13","cited_by_count":17,"area":"safety"},{"id":"2510.19422","title":"LLM Unlearning with LLM Beliefs","created":"2025-10-22","cited_by_count":17,"area":"safety"},{"id":"2502.11441","title":"Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning","created":"2025-02-17","cited_by_count":16,"area":"safety"},{"id":"2510.27062","title":"Consistency Training Helps Stop Sycophancy and Jailbreaks","created":"2025-10-31","cited_by_count":16,"area":"safety"},{"id":"2506.15699","title":"BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap","created":"2025-05-28","cited_by_count":15,"area":"safety"},{"id":"2410.15153","title":"Evaluating Deep Unlearning in Large Language Models","created":"2024-10-19","cited_by_count":14,"area":"safety"},{"id":"2502.17823","title":"A General Framework to Enhance Fine-tuning-based LLM Unlearning","created":"2025-02-25","cited_by_count":14,"area":"safety"},{"id":"2504.07467","title":"Defense against Prompt Injection Attacks via Mixture of Encodings","created":"2025-04-10","cited_by_count":14,"area":"safety"},{"id":"2506.05735","title":"Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness","created":"2025-06-06","cited_by_count":14,"area":"safety"},{"id":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"id":"2407.11282","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","created":"2024-07-15","cited_by_count":13,"area":"safety"},{"id":"2505.19056","title":"An Embarrassingly Simple Defense Against LLM Abliteration Attacks","created":"2025-05-25","cited_by_count":13,"area":"safety"},{"id":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"safety"},{"id":"2410.06467","title":"WAPITI: A Watermark for Finetuned Open-Source LLMs","created":"2024-10-09","cited_by_count":12,"area":"safety"},{"id":"2504.10185","title":"LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks","created":"2025-04-14","cited_by_count":12,"area":"safety"},{"id":"2509.24296","title":"DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models","created":"2025-09-29","cited_by_count":12,"area":"safety"},{"id":"2411.06899","title":"LongSafety: Enhance Safety for Long-Context LLMs","created":"2024-11-11","cited_by_count":11,"area":"safety"},{"id":"2502.05911","title":"GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation","created":"2025-02-09","cited_by_count":11,"area":"safety"},{"id":"2504.07113","title":"How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities","created":"2025-03-20","cited_by_count":11,"area":"safety"},{"id":"2505.16947","title":"MixAT: Combining Continuous and Discrete Adversarial Training for LLMs","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2506.09227","title":"SoK: Machine Unlearning for Large Language Models","created":"2025-06-10","cited_by_count":11,"area":"safety"},{"id":"2506.14003","title":"Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs","created":"2025-06-16","cited_by_count":11,"area":"safety"}],"next_cursor":"100"}