{"total":264,"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":"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":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"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":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"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":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110,"area":"safety"},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","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":"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":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79,"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":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76,"area":"safety"},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63,"area":"safety"},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62,"area":"safety"},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"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":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","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":"2501.15145","title":"PromptShield: Deployable Detection for Prompt Injection Attacks","created":"2025-01-25","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":"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":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45,"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":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"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":"2311.15766","title":"Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges","created":"2023-11-27","cited_by_count":38,"area":"safety"},{"id":"2304.07361","title":"PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators","created":"2023-04-14","cited_by_count":37,"area":"safety"},{"id":"2206.11349","title":"Prompt Injection: Parameterization of Fixed Inputs","created":"2022-05-31","cited_by_count":36,"area":"safety"},{"id":"2405.19360","title":"ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users","created":"2024-05-24","cited_by_count":35,"area":"safety"},{"id":"2410.02760","title":"Erasing Conceptual Knowledge from Language Models","created":"2024-10-03","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":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","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":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31,"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":"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":"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":"2410.14425","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","created":"2024-10-18","cited_by_count":27,"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":"2406.10952","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","created":"2024-06-16","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":"2411.00154","title":"Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models","created":"2024-10-31","cited_by_count":24,"area":"safety"},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2403.09562","title":"PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps","created":"2024-03-14","cited_by_count":23,"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":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2406.05344","title":"MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention","created":"2024-06-08","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":"2508.11548","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","created":"2025-08-15","cited_by_count":20,"area":"safety"},{"id":"2409.09778","title":"Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions","created":"2024-09-15","cited_by_count":19,"area":"safety"},{"id":"2406.14796","title":"MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning","created":"2024-06-21","cited_by_count":17,"area":"safety"},{"id":"2410.02684","title":"HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2407.04411","title":"Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs","created":"2024-07-05","cited_by_count":15,"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":"2310.11397","title":"Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning","created":"2023-10-17","cited_by_count":14,"area":"safety"},{"id":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14,"area":"safety"},{"id":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","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":"2505.14483","title":"MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance","created":"2025-05-20","cited_by_count":13,"area":"safety"},{"id":"2408.05131","title":"Range Membership Inference Attacks","created":"2024-08-09","cited_by_count":12,"area":"safety"},{"id":"2410.21083","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","created":"2024-10-28","cited_by_count":12,"area":"safety"},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2509.09703","title":"CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor","created":"2025-09-05","cited_by_count":12,"area":"safety"},{"id":"2306.11648","title":"Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in Astronomy","created":"2023-06-20","cited_by_count":11,"area":"safety"},{"id":"2403.08481","title":"SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks","created":"2024-03-13","cited_by_count":11,"area":"safety"},{"id":"2407.01376","title":"Badllama 3: removing safety finetuning from Llama 3 in minutes","created":"2024-07-01","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":"2502.18511","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","created":"2025-02-22","cited_by_count":11,"area":"safety"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","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":"2506.12551","title":"MEraser: An Effective Fingerprint Erasure Approach for Large Language Models","created":"2025-06-14","cited_by_count":11,"area":"safety"},{"id":"2311.09535","title":"Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection","created":"2023-11-16","cited_by_count":10,"area":"safety"},{"id":"2410.06913","title":"Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning","created":"2024-10-09","cited_by_count":10,"area":"safety"},{"id":"2501.18632","title":"Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare","created":"2025-01-27","cited_by_count":10,"area":"safety"},{"id":"2502.11647","title":"DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing","created":"2025-02-17","cited_by_count":10,"area":"safety"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2407.12281","title":"Turning Generative Models Degenerate: The Power of Data Poisoning Attacks","created":"2024-07-17","cited_by_count":9,"area":"safety"},{"id":"2412.02454","title":"Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining","created":"2024-12-03","cited_by_count":9,"area":"safety"},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9,"area":"safety"},{"id":"2508.01365","title":"ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models","created":"2025-08-02","cited_by_count":9,"area":"safety"},{"id":"2511.05797","title":"When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins","created":"2025-11-08","cited_by_count":9,"area":"safety"},{"id":"2309.05940","title":"Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking","created":"2023-09-12","cited_by_count":8,"area":"safety"},{"id":"2401.01085","title":"Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control","created":"2024-01-02","cited_by_count":8,"area":"safety"},{"id":"2402.12026","title":"Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space","created":"2024-02-19","cited_by_count":8,"area":"safety"},{"id":"2403.14725","title":"Testing the Limits of Jailbreaking Defenses with the Purple Problem","created":"2024-03-20","cited_by_count":8,"area":"safety"},{"id":"2505.16530","title":"DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection","created":"2025-05-22","cited_by_count":8,"area":"safety"},{"id":"2605.01687","title":"MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety","created":"2026-05-03","cited_by_count":8,"area":"safety"},{"id":"2308.07847","title":"Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models","created":"2023-08-15","cited_by_count":7,"area":"safety"},{"id":"2310.07219","title":"Improved Membership Inference Attacks Against Language Classification Models","created":"2023-10-11","cited_by_count":7,"area":"safety"},{"id":"2405.02365","title":"ModelShield: Adaptive and Robust Watermark against Model Extraction Attack","created":"2024-05-03","cited_by_count":7,"area":"safety"}],"next_cursor":"100"}