{"total":83,"rows":[{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129,"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":"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":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"area":"safety"},{"id":"2410.19278","title":"Applying sparse autoencoders to unlearn knowledge in language models","created":"2024-10-25","cited_by_count":59,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"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":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"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":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"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":"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":"2410.09591","title":"Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy","created":"2024-10-12","cited_by_count":17,"area":"safety"},{"id":"2506.07171","title":"RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality","created":"2025-06-08","cited_by_count":16,"area":"safety"},{"id":"2412.06966","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research","created":"2024-12-09","cited_by_count":15,"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":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","cited_by_count":14,"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":"2505.22310","title":"From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization","created":"2025-05-28","cited_by_count":12,"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":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","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"},{"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":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","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":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2506.00688","title":"Existing Large Language Model Unlearning Evaluations Are Inconclusive","created":"2025-05-31","cited_by_count":8,"area":"safety"},{"id":"2502.12430","title":"Position: Bridge the Gaps between Machine Unlearning and AI Regulation","created":"2025-02-18","cited_by_count":7,"area":"safety"},{"id":"2505.23270","title":"Does Machine Unlearning Truly Remove Knowledge?","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2502.19982","title":"Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models","created":"2025-02-27","cited_by_count":5,"area":"safety"},{"id":"2505.24379","title":"Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM","created":"2025-05-30","cited_by_count":5,"area":"safety"},{"id":"2506.10236","title":"Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods","created":"2025-06-11","cited_by_count":5,"area":"safety"},{"id":"2512.19025","title":"The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation","created":"2025-12-22","cited_by_count":5,"area":"safety"},{"id":"2506.12484","title":"Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization","created":"2025-06-14","cited_by_count":4,"area":"safety"},{"id":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2508.15449","title":"Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection","created":"2025-08-21","cited_by_count":4,"area":"safety"},{"id":"2509.22483","title":"OFMU: Optimization-Driven Framework for Machine Unlearning","created":"2025-09-26","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":"2604.07962","title":"Is your algorithm unlearning or untraining?","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2508.17233","title":"Module-Aware Parameter-Efficient Machine Unlearning on Transformers","created":"2025-08-24","cited_by_count":3,"area":"safety"},{"id":"2509.11816","title":"Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning","created":"2025-09-15","cited_by_count":3,"area":"safety"},{"id":"2601.15111","title":"Auditing Language Model Unlearning via Information Decomposition","created":"2026-01-21","cited_by_count":3,"area":"safety"},{"id":"2601.21283","title":"DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher","created":"2026-01-29","cited_by_count":3,"area":"safety"},{"id":"2606.27379","title":"Position: The Term \"Machine Unlearning\" Is Overused in LLMs","created":"2026-05-08","cited_by_count":3,"area":"safety"},{"id":"2502.15836","title":"Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2503.00917","title":"AMUN: Adversarial Machine UNlearning","created":"2025-03-02","cited_by_count":2,"area":"safety"},{"id":"2510.07626","title":"LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics","created":"2025-10-08","cited_by_count":2,"area":"safety"},{"id":"2510.09007","title":"LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data","created":"2025-10-10","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":"2602.22562","title":"Layer-Targeted Multilingual Knowledge Erasure in Large Language Models","created":"2026-02-26","cited_by_count":2,"area":"safety"},{"id":"2504.06407","title":"Understanding Machine Unlearning Through the Lens of Mode Connectivity","created":"2025-04-08","cited_by_count":1,"area":"safety"},{"id":"2508.20443","title":"Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2509.20230","title":"Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization","created":"2025-09-24","cited_by_count":1,"area":"safety"},{"id":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2602.03379","title":"Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures","created":"2026-02-03","cited_by_count":1,"area":"safety"},{"id":"2603.00823","title":"A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction","created":"2026-02-28","cited_by_count":1,"area":"safety"},{"id":"2605.08765","title":"Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning","created":"2026-05-09","cited_by_count":1,"area":"safety"},{"id":"2605.11685","title":"Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter","created":"2026-05-12","cited_by_count":1,"area":"safety"},{"id":"2605.26526","title":"Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks","created":"2026-05-26","cited_by_count":1,"area":"safety"},{"id":"2608.11408","title":"Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning","created":"2026-08-11","cited_by_count":1,"area":"safety"},{"id":"2601.22601","title":"Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning","created":"2026-01-30","cited_by_count":0,"area":"safety"},{"id":"2602.01703","title":"$\\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2604.06154","title":"Exclusive Unlearning","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2604.15482","title":"Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation","created":"2026-04-16","cited_by_count":0,"area":"safety"},{"id":"2605.07482","title":"SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2606.17168","title":"RepSelect: Robust LLM Unlearning via Representation Selectivity","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2607.16227","title":"LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.23970","title":"Understanding Machine Unlearning Through the Lens of Mode Connectivity","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2608.14229","title":"The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning","created":"2026-08-14","cited_by_count":0,"area":"safety"},{"id":"2608.22527","title":"Stress Testing Unlearning Algorithms","created":"2026-08-23","cited_by_count":0,"area":"safety"},{"id":"2608.25429","title":"Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2609.00445","title":"Capability-Gated Language Models: Security Composes, Utility Does Not","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.16229","title":"Test-Time Unlearning via Sparse Autoencoder","created":"2026-09-14","cited_by_count":0,"area":"safety"},{"id":"2609.21996","title":"A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.34591","title":"TULIP: Targeted LLM Unlearning at Layers Identified Per-Input","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2609.36612","title":"Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.38909","title":"Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.03502","title":"Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation","created":"2026-10-02","cited_by_count":0,"area":"safety"},{"id":"2610.19385","title":"RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning","created":"2026-10-14","cited_by_count":0,"area":"safety"}],"next_cursor":null}