{"total":124,"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":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"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":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"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":"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":"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":"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":"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":"2402.10052","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2406.12038","title":"Soft Prompting for Unlearning in Large Language Models","created":"2024-06-17","cited_by_count":46,"area":"safety"},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43,"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":"2402.05813","title":"Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models","created":"2024-02-08","cited_by_count":39,"area":"safety"},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"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":"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":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"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":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"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":"2411.15477","title":"Towards Robust Evaluation of Unlearning in LLMs via Data Transformations","created":"2024-11-23","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":"2502.11598","title":"Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?","created":"2025-02-17","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":"2506.07596","title":"TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts","created":"2025-06-09","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":"2409.11844","title":"MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts","created":"2024-09-18","cited_by_count":18,"area":"safety"},{"id":"2405.16720","title":"Large Scale Knowledge Washing","created":"2024-05-26","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":"2405.07667","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","created":"2024-05-13","cited_by_count":12,"area":"safety"},{"id":"2406.13748","title":"Learn and Unlearn: Addressing Misinformation in Multilingual LLMs","created":"2024-06-19","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":"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":"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":"2504.17480","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":"2505.16947","title":"MixAT: Combining Continuous and Discrete Adversarial Training for LLMs","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2512.21008","title":"GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs","created":"2025-12-24","cited_by_count":11,"area":"safety"},{"id":"2406.12329","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","created":"2024-06-18","cited_by_count":10,"area":"safety"},{"id":"2406.14091","title":"Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models","created":"2024-06-20","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":"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":"2505.17601","title":"Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs","created":"2025-05-23","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":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2410.13274","title":"Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning","created":"2024-10-17","cited_by_count":8,"area":"safety"},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2406.13551","title":"Mitigating Social Biases in Language Models through Unlearning","created":"2024-06-19","cited_by_count":7,"area":"safety"},{"id":"2603.13461","title":"Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference","created":"2026-03-13","cited_by_count":7,"area":"safety"},{"id":"2607.19829","title":"DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection","created":"2026-07-22","cited_by_count":6,"area":"safety"},{"id":"2407.20271","title":"Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models","created":"2024-07-25","cited_by_count":5,"area":"safety"},{"id":"2409.13054","title":"LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models","created":"2024-09-19","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":"2503.11185","title":"Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks","created":"2025-03-14","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":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"area":"safety"},{"id":"2510.02962","title":"Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking","created":"2025-10-03","cited_by_count":5,"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":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","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":"2508.12072","title":"Mitigating Jailbreaks with Intent-Aware LLMs","created":"2025-08-16","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":"2510.25117","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":"2408.09459","title":"WPN: An Unlearning Method Based on N-pair Contrastive Learning in Language Models","created":"2024-08-18","cited_by_count":3,"area":"safety"},{"id":"2511.07842","title":"Safety-Preserving PTQ via Contrastive Alignment Loss","created":"2025-11-11","cited_by_count":3,"area":"safety"},{"id":"2603.03323","title":"Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement","created":"2026-02-10","cited_by_count":3,"area":"safety"},{"id":"2503.22539","title":"Efficient Verified Machine Unlearning For Distillation","created":"2025-03-28","cited_by_count":2,"area":"safety"},{"id":"2504.05689","title":"Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2505.03501","title":"BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models","created":"2025-05-06","cited_by_count":2,"area":"safety"},{"id":"2510.01342","title":"Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach","created":"2025-10-01","cited_by_count":2,"area":"safety"},{"id":"2510.07775","title":"The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs","created":"2025-10-09","cited_by_count":2,"area":"safety"},{"id":"2602.02824","title":"CALIBURN: Self-Calibrated LLM Unlearning Alignment","created":"2026-02-02","cited_by_count":2,"area":"safety"},{"id":"2607.02513","title":"LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning","created":"2026-07-02","cited_by_count":2,"area":"safety"},{"id":"2607.18639","title":"Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs","created":"2026-07-21","cited_by_count":2,"area":"safety"},{"id":"2402.03303","title":"Nevermind: Instruction Override and Moderation in Large Language Models","created":"2024-02-05","cited_by_count":1,"area":"safety"},{"id":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2509.15621","title":"Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2511.12217","title":"AlignTree: Efficient Defense Against LLM Jailbreak Attacks","created":"2025-11-15","cited_by_count":1,"area":"safety"},{"id":"2511.19009","title":"Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2511.19566","title":"ModHiFi: Identifying High Fidelity predictive components for Model Modification","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2601.04261","title":"Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models","created":"2026-01-07","cited_by_count":1,"area":"safety"},{"id":"2601.08189","title":"ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models","created":"2026-01-13","cited_by_count":1,"area":"safety"},{"id":"2602.06623","title":"Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2603.29038","title":"Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning","created":"2026-03-30","cited_by_count":1,"area":"safety"},{"id":"2606.03785","title":"Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs","created":"2026-06-02","cited_by_count":1,"area":"safety"},{"id":"2607.26849","title":"ToxScreen: Detecting Whether an LLM Has Been Poisoned","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2609.25049","title":"Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration","created":"2026-09-06","cited_by_count":1,"area":"safety"},{"id":"2507.20650","title":"Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution","created":"2025-07-28","cited_by_count":0,"area":"safety"},{"id":"2601.04275","title":"Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs","created":"2026-01-07","cited_by_count":0,"area":"safety"},{"id":"2601.10566","title":"Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure","created":"2026-01-15","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}