{"total":36,"rows":[{"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":"2409.01193","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","created":"2024-09-02","cited_by_count":13,"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":"2305.14851","title":"Sharpness-Aware Data Poisoning Attack","created":"2023-05-24","cited_by_count":10,"area":"safety"},{"id":"2403.08618","title":"SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness","created":"2024-03-13","cited_by_count":10,"area":"safety"},{"id":"2404.13518","title":"Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion","created":"2024-04-21","cited_by_count":9,"area":"safety"},{"id":"2510.07835","title":"MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation","created":"2025-10-09","cited_by_count":8,"area":"safety"},{"id":"2602.06441","title":"Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning","created":"2026-02-06","cited_by_count":6,"area":"safety"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2110.05524","title":"Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference","created":"2021-10-11","cited_by_count":5,"area":"safety"},{"id":"2407.02747","title":"Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature","created":"2024-07-03","cited_by_count":5,"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":"2510.00761","title":"Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2602.06248","title":"REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop","created":"2026-02-05","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":"2407.14738","title":"Flatness-aware Sequential Learning Generates Resilient Backdoors","created":"2024-07-20","cited_by_count":3,"area":"safety"},{"id":"2504.06398","title":"Sharpness-Aware Parameter Selection for Machine Unlearning","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","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":"2605.16776","title":"Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning","created":"2026-05-16","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":"2507.23291","title":"Evaluating the Dynamics of Membership Privacy in Deep Learning","created":"2025-07-31","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":"2602.21773","title":"Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias","created":"2026-02-25","cited_by_count":1,"area":"safety"},{"id":"2605.02196","title":"DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning","created":"2026-05-04","cited_by_count":1,"area":"safety"},{"id":"2609.27355","title":"Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction","created":"2026-09-23","cited_by_count":1,"area":"safety"},{"id":"2512.03437","title":"Grokked Models are Better Unlearners","created":"2025-12-03","cited_by_count":0,"area":"safety"},{"id":"2602.02139","title":"EvoMU: Evolutionary Machine Unlearning","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.02986","title":"Why Some Models Resist Unlearning: A Linear Stability Perspective","created":"2026-02-03","cited_by_count":0,"area":"safety"},{"id":"2602.11213","title":"Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation","created":"2026-02-11","cited_by_count":0,"area":"safety"},{"id":"2603.22987","title":"A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks","created":"2026-03-24","cited_by_count":0,"area":"safety"},{"id":"2605.05871","title":"Retain-Neutral Surrogates for Min-Max Unlearning","created":"2026-05-07","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":"2608.16249","title":"SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning","created":"2026-08-17","cited_by_count":0,"area":"safety"},{"id":"2609.25166","title":"Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning","created":"2026-09-21","cited_by_count":0,"area":"safety"},{"id":"2609.37076","title":"UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?","created":"2026-09-29","cited_by_count":0,"area":"safety"}],"next_cursor":null}