{"total":73,"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":"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":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"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":"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":"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":"2502.17823","title":"A General Framework to Enhance Fine-tuning-based LLM Unlearning","created":"2025-02-25","cited_by_count":14,"area":"safety"},{"id":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","cited_by_count":14,"area":"safety"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"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":"2505.15962","title":"Pre-training Limited Memory Language Models with Internal and External Knowledge","created":"2025-05-21","cited_by_count":12,"area":null},{"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":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","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"},{"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":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2506.00359","title":"Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy","created":"2025-05-31","cited_by_count":9,"area":"safety"},{"id":"2506.04410","title":"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2506.00688","title":"Existing Large Language Model Unlearning Evaluations Are Inconclusive","created":"2025-05-31","cited_by_count":8,"area":"safety"},{"id":"2506.17279","title":"Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models","created":"2025-06-14","cited_by_count":6,"area":"lr"},{"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":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"area":"safety"},{"id":"2505.18786","title":"Leveraging Per-Instance Privacy for Machine Unlearning","created":"2025-05-24","cited_by_count":4,"area":"safety"},{"id":"2506.01318","title":"Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack","created":"2025-06-02","cited_by_count":4,"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":"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":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.10568","title":"Gauss-Newton Unlearning for the LLM Era","created":"2026-02-11","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":"2505.09341","title":"Access Controls Will Solve the Dual-Use Dilemma","created":"2025-05-14","cited_by_count":3,"area":null},{"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":"2607.08077","title":"Modular Pretraining Enables Access Control","created":"2026-07-09","cited_by_count":3,"area":null},{"id":"2507.07754","title":"One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting","created":"2025-07-10","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":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2504.05059","title":"MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Prediction","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.09500","title":"Layered Unlearning for Adversarial Relearning","created":"2025-05-14","cited_by_count":1,"area":"safety"},{"id":"2601.16527","title":"Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs","created":"2026-01-23","cited_by_count":1,"area":"mllm"},{"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":"2604.15717","title":"Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries","created":"2026-04-17","cited_by_count":1,"area":"alignment"},{"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":"2608.04692","title":"Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies","created":"2026-08-05","cited_by_count":1,"area":"vla"},{"id":"2608.11408","title":"Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning","created":"2026-08-11","cited_by_count":1,"area":"safety"},{"id":"2511.06803","title":"Learning to Fast Unrank in Collaborative Filtering Recommendation","created":"2025-11-10","cited_by_count":0,"area":null},{"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"},{"id":"2603.00133","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","created":"2026-02-23","cited_by_count":0,"area":"diffusion"},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.09391","title":"Efficient Unlearning through Maximizing Relearning Convergence Delay","created":"2026-04-10","cited_by_count":0,"area":"safety"},{"id":"2604.13438","title":"WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework","created":"2026-04-15","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":"2605.26454","title":"Model Unlearning Objectives Vary for Distinct Language Functions","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2606.03695","title":"Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.09559","title":"Safe-RULE: Safe Reinforcement UnLEarning","created":"2026-06-08","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":"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":"2608.29943","title":"On the Recoverability of Private Information Unlearning in Large Language Models","created":"2026-08-30","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":"2609.02018","title":"Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning","created":"2026-09-02","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":"2609.32103","title":"LLM Unlearning Evaluation with TRIAGE","created":"2026-09-26","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":"2610.09004","title":"Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.17659","title":"Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}