{"total":164,"rows":[{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443,"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":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560,"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":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302,"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":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139,"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":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114,"area":"safety"},{"id":"2312.07913","title":"A Survey of Text Watermarking in the Era of Large Language Models","created":"2023-12-13","cited_by_count":112,"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":"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":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"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":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"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":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75,"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":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"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":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"area":"safety"},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","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":"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":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"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":"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":"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":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"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":"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":"2505.11413","title":"CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs","created":"2025-05-16","cited_by_count":26,"area":"safety"},{"id":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","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":"2505.11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","created":"2025-05-14","cited_by_count":24,"area":"safety"},{"id":"2501.07238","title":"Lessons From Red Teaming 100 Generative AI Products","created":"2025-01-13","cited_by_count":23,"area":"safety"},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23,"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":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2502.11598","title":"Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?","created":"2025-02-17","cited_by_count":19,"area":"safety"},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"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":"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":"2505.24428","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections","created":"2025-05-30","cited_by_count":18,"area":"safety"},{"id":"2404.16841","title":"Machine Unlearning in Large Language Models","created":"2024-02-03","cited_by_count":17,"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"},{"id":"2510.21189","title":"Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency","created":"2025-10-24","cited_by_count":17,"area":"safety"},{"id":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"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":"2411.06899","title":"LongSafety: Enhance Safety for Long-Context LLMs","created":"2024-11-11","cited_by_count":11,"area":"safety"},{"id":"2503.01742","title":"Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models","created":"2025-03-03","cited_by_count":11,"area":"safety"},{"id":"2503.02174","title":"Adversarial Tokenization","created":"2025-03-04","cited_by_count":11,"area":"safety"},{"id":"2504.17480","title":"Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation","created":"2025-04-24","cited_by_count":11,"area":"safety"},{"id":"2509.02820","title":"Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs","created":"2025-09-02","cited_by_count":11,"area":"safety"},{"id":"2503.04693","title":"UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets","created":"2025-03-06","cited_by_count":10,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2505.08878","title":"Optimized Couplings for Watermarking Large Language Models","created":"2025-05-13","cited_by_count":9,"area":"safety"},{"id":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2409.15361","title":"Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning","created":"2024-09-18","cited_by_count":8,"area":"safety"},{"id":"2502.08142","title":"Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences","created":"2025-02-12","cited_by_count":8,"area":"safety"},{"id":"2504.19674","title":"SAGE: A Generic Framework for LLM Safety Evaluation","created":"2025-04-28","cited_by_count":8,"area":"safety"},{"id":"2509.20977","title":"CLUE: Conflict-guided Localization for LLM Unlearning Framework","created":"2025-09-25","cited_by_count":7,"area":"safety"},{"id":"2405.12604","title":"Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming","created":"2024-05-21","cited_by_count":6,"area":"safety"},{"id":"2411.03806","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","created":"2024-11-06","cited_by_count":6,"area":"safety"},{"id":"2504.00446","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","created":"2025-04-01","cited_by_count":6,"area":"safety"},{"id":"2510.17021","title":"Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning","created":"2025-10-19","cited_by_count":6,"area":"safety"},{"id":"2601.05641","title":"Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs","created":"2026-01-09","cited_by_count":6,"area":"safety"},{"id":"2311.09473","title":"JAB: Joint Adversarial Prompting and Belief Augmentation","created":"2023-11-16","cited_by_count":5,"area":"safety"},{"id":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"area":"safety"},{"id":"2410.10150","title":"Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting","created":"2024-10-14","cited_by_count":5,"area":"safety"},{"id":"2502.15010","title":"Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models","created":"2025-02-20","cited_by_count":5,"area":"safety"},{"id":"2505.16567","title":"Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning","created":"2025-05-22","cited_by_count":5,"area":"safety"},{"id":"2510.15476","title":"SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses","created":"2025-10-17","cited_by_count":5,"area":"safety"},{"id":"2403.09832","title":"Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks","created":"2024-03-14","cited_by_count":4,"area":"safety"},{"id":"2406.10847","title":"TorchOpera: A Compound AI System for LLM Safety","created":"2024-06-16","cited_by_count":4,"area":"safety"},{"id":"2412.03107","title":"CredID: Credible Multi-Bit Watermark for Large Language Models Identification","created":"2024-12-04","cited_by_count":4,"area":"safety"},{"id":"2502.16174","title":"Efficient LLM Moderation with Multi-Layer Latent Prototypes","created":"2025-02-22","cited_by_count":4,"area":"safety"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2505.06027","title":"Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation","created":"2025-05-09","cited_by_count":4,"area":"safety"},{"id":"2505.15209","title":"DUSK: Do Not Unlearn Shared Knowledge","created":"2025-05-21","cited_by_count":4,"area":"safety"},{"id":"2507.18203","title":"Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation","created":"2025-07-24","cited_by_count":4,"area":"safety"},{"id":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","cited_by_count":4,"area":"safety"},{"id":"2508.15182","title":"SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks","created":"2025-08-21","cited_by_count":4,"area":"safety"},{"id":"2510.00761","title":"Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2510.16367","title":"EditMark: Watermarking Large Language Models based on Model Editing","created":"2025-10-18","cited_by_count":4,"area":"safety"},{"id":"2510.25117","title":"A Survey on Unlearning in Large Language Models","created":"2025-10-29","cited_by_count":4,"area":"safety"},{"id":"2511.00030","title":"Probing Knowledge Holes in Unlearned LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"}],"next_cursor":"100"}