{"total":81,"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":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"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":"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":"2508.00890","title":"AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks","created":"2025-07-26","cited_by_count":16,"area":"lr"},{"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":"2503.14530","title":"SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders","created":"2025-03-16","cited_by_count":13,"area":"mllm"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"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":"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":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2604.03956","title":"VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models","created":"2026-04-05","cited_by_count":10,"area":"vla"},{"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":"2603.14819","title":"RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models","created":"2026-03-16","cited_by_count":8,"area":"mllm"},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2505.12636","title":"Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2508.17222","title":"Exposing Privacy Risks in Graph Retrieval-Augmented Generation","created":"2025-08-24","cited_by_count":5,"area":"rag"},{"id":"2510.12981","title":"Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check","created":"2025-10-14","cited_by_count":5,"area":"safety"},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2604.19884","title":"From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization","created":"2026-04-21","cited_by_count":5,"area":null},{"id":"2505.15209","title":"DUSK: Do Not Unlearn Shared Knowledge","created":"2025-05-21","cited_by_count":4,"area":"safety"},{"id":"2506.00808","title":"Unlearning Inversion Attacks for Graph Neural Networks","created":"2025-06-01","cited_by_count":4,"area":null},{"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":"2506.17265","title":"SUA: Stealthy Multimodal Large Language Model Unlearning Attack","created":"2025-06-10","cited_by_count":4,"area":"mllm"},{"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":"2512.18035","title":"Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models","created":"2025-12-19","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":"2602.06248","title":"REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop","created":"2026-02-05","cited_by_count":4,"area":"safety"},{"id":"2506.13181","title":"Align-then-Unlearn: Embedding Alignment for LLM Unlearning","created":"2025-06-16","cited_by_count":3,"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":"2511.12991","title":"Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2602.13151","title":"Quantization-Robust LLM Unlearning via Low-Rank Adaptation","created":"2026-02-13","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":"2506.10946","title":"GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models","created":"2025-06-12","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":"2601.22030","title":"Per-parameter Task Arithmetic for Unlearning in Large Language Models","created":"2026-01-29","cited_by_count":2,"area":"safety"},{"id":"2602.19275","title":"KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models","created":"2026-02-22","cited_by_count":2,"area":"safety"},{"id":"2605.12765","title":"Inference-Time Machine Unlearning via Gated Activation Redirection","created":"2026-05-12","cited_by_count":2,"area":"safety"},{"id":"2606.13873","title":"Natively Unlearnable Large Language Models","created":"2026-06-11","cited_by_count":2,"area":"safety"},{"id":"2609.10439","title":"Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs","created":"2026-09-09","cited_by_count":2,"area":"safety"},{"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":"2512.00272","title":"WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols","created":"2025-11-29","cited_by_count":1,"area":"safety"},{"id":"2601.15538","title":"QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs","created":"2026-01-21","cited_by_count":1,"area":"safety"},{"id":"2602.05252","title":"Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks","created":"2026-02-05","cited_by_count":1,"area":"safety"},{"id":"2603.06640","title":"Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models","created":"2026-02-28","cited_by_count":1,"area":"diffusion"},{"id":"2603.18570","title":"Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.22076","title":"PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning","created":"2026-04-23","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":"2605.05678","title":"Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.15138","title":"Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution","created":"2026-05-14","cited_by_count":1,"area":"safety"},{"id":"2608.05783","title":"GROM: Gradient-Free Rapid One-Shot Machine Unlearning","created":"2026-08-06","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":"2608.18578","title":"Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2608.24988","title":"Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal","created":"2026-08-25","cited_by_count":1,"area":"mechinterp"},{"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":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","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":"2602.02139","title":"EvoMU: Evolutionary Machine Unlearning","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.19215","title":"Understanding Empirical Unlearning with Combinatorial Interpretability","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2605.01699","title":"Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance","created":"2026-05-03","cited_by_count":0,"area":"safety"},{"id":"2605.05687","title":"DataDignity: Training Data Attribution for Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2606.02920","title":"Fast Unlearning at Scale via Margin Self-Correction","created":"2026-06-01","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":"2607.16442","title":"One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models","created":"2026-07-17","cited_by_count":0,"area":"mllm"},{"id":"2607.25451","title":"Bits and Memories: Measuring Verbatim Extraction Across LLM Quantization","created":"2026-07-28","cited_by_count":0,"area":"safety"},{"id":"2607.28829","title":"When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks","created":"2026-07-30","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":"2609.11490","title":"Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints","created":"2026-09-10","cited_by_count":0,"area":"safety"},{"id":"2609.14060","title":"AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.16229","title":"Test-Time Unlearning via Sparse Autoencoder","created":"2026-09-14","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":"2609.39279","title":"Faithful Dual-constrained Erasure for Robust LLM Safety Alignment","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","created":"2026-10-01","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}