{"total":113,"rows":[{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"area":"safety"},{"id":"2304.04934","title":"Model Sparsity Can Simplify Machine Unlearning","created":"2023-04-11","cited_by_count":214,"area":"safety"},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110,"area":"safety"},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62,"area":"safety"},{"id":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52,"area":"safety"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47,"area":"safety"},{"id":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45,"area":"safety"},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"area":"safety"},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"id":"2405.19360","title":"ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users","created":"2024-05-24","cited_by_count":35,"area":"safety"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28,"area":"safety"},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23,"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":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","cited_by_count":22,"area":"safety"},{"id":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","cited_by_count":20,"area":"safety"},{"id":"2405.09879","title":"Generative Unlearning for Any Identity","created":"2024-05-16","cited_by_count":19,"area":"safety"},{"id":"2503.06339","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","created":"2025-03-08","cited_by_count":19,"area":"safety"},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2406.14796","title":"MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning","created":"2024-06-21","cited_by_count":17,"area":"safety"},{"id":"2407.07485","title":"Zero-Shot Class Unlearning in CLIP with Synthetic Samples","created":"2024-07-10","cited_by_count":17,"area":"safety"},{"id":"2411.15537","title":"MUNBa: Machine Unlearning via Nash Bargaining","created":"2024-11-23","cited_by_count":17,"area":"safety"},{"id":"2501.03544","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","created":"2025-01-07","cited_by_count":17,"area":"safety"},{"id":"2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","created":"2026-04-22","cited_by_count":17,"area":"safety"},{"id":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2406.08288","title":"Decoupling the Class Label and the Target Concept in Machine Unlearning","created":"2024-06-12","cited_by_count":12,"area":"safety"},{"id":"2408.00376","title":"On the Limitations and Prospects of Machine Unlearning for Generative AI","created":"2024-08-01","cited_by_count":12,"area":"safety"},{"id":"2503.13769","title":"Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion","created":"2025-03-17","cited_by_count":12,"area":"safety"},{"id":"2506.02761","title":"Rethinking Machine Unlearning in Image Generation Models","created":"2025-06-03","cited_by_count":9,"area":"safety"},{"id":"2508.03696","title":"PLA: Prompt Learning Attack against Text-to-Image Generative Models","created":"2025-07-14","cited_by_count":9,"area":"safety"},{"id":"2305.11351","title":"Data Redaction from Conditional Generative Models","created":"2023-05-18","cited_by_count":8,"area":"safety"},{"id":"2505.21074","title":"Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling","created":"2025-05-27","cited_by_count":8,"area":"safety"},{"id":"2603.01285","title":"Attention Smoothing Is All You Need For Unlearning","created":"2026-03-01","cited_by_count":7,"area":"safety"},{"id":"2309.11575","title":"Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge","created":"2023-09-20","cited_by_count":6,"area":"safety"},{"id":"2504.15827","title":"DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers","created":"2025-04-22","cited_by_count":6,"area":"safety"},{"id":"2507.20140","title":"Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech","created":"2025-07-27","cited_by_count":6,"area":"safety"},{"id":"2508.15127","title":"Towards Source-Free Machine Unlearning","created":"2025-08-20","cited_by_count":6,"area":"safety"},{"id":"2510.24034","title":"AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts","created":"2025-10-28","cited_by_count":6,"area":"safety"},{"id":"2601.00590","title":"SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation","created":"2026-01-02","cited_by_count":6,"area":"safety"},{"id":"2312.14895","title":"FAST: Feature Aware Similarity Thresholding for Weak Unlearning in Black-Box Generative Models","created":"2023-12-22","cited_by_count":5,"area":"safety"},{"id":"2408.01689","title":"Controllable Unlearning for Image-to-Image Generative Models via $\\varepsilon$-Constrained Optimization","created":"2024-08-03","cited_by_count":5,"area":"safety"},{"id":"2503.01839","title":"Jailbreaking Safeguarded Text-to-Image Models via Large Language Models","created":"2025-03-03","cited_by_count":5,"area":"safety"},{"id":"2505.21347","title":"OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models","created":"2025-05-27","cited_by_count":5,"area":"safety"},{"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":"2510.22124","title":"Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery","created":"2025-10-25","cited_by_count":5,"area":"safety"},{"id":"2411.12600","title":"Provable unlearning in topic modeling and downstream tasks","created":"2024-11-19","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":"2510.23960","title":"SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability","created":"2025-10-28","cited_by_count":4,"area":"safety"},{"id":"2511.18684","title":"Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation","created":"2025-11-24","cited_by_count":4,"area":"safety"},{"id":"2601.22359","title":"The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples","created":"2026-01-29","cited_by_count":4,"area":"safety"},{"id":"2412.07249","title":"Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation","created":"2024-12-10","cited_by_count":3,"area":"safety"},{"id":"2503.18674","title":"Human Motion Unlearning","created":"2025-03-24","cited_by_count":3,"area":"safety"},{"id":"2506.18325","title":"NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation","created":"2025-06-23","cited_by_count":3,"area":"safety"},{"id":"2507.22499","title":"LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning","created":"2025-07-30","cited_by_count":3,"area":"safety"},{"id":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","cited_by_count":3,"area":"safety"},{"id":"2601.08623","title":"SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2603.15033","title":"Models Designed to Forget: Machine Unlearning via Key Deletion","created":"2026-03-16","cited_by_count":3,"area":"safety"},{"id":"2402.06864","title":"Discriminative Adversarial Unlearning","created":"2024-02-10","cited_by_count":2,"area":"safety"},{"id":"2405.15517","title":"Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction","created":"2024-05-24","cited_by_count":2,"area":"safety"},{"id":"2504.05838","title":"Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2506.20941","title":"Revisiting the Past: Data Unlearning with Model State History","created":"2025-06-26","cited_by_count":2,"area":"safety"},{"id":"2507.21985","title":"ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models","created":"2025-07-29","cited_by_count":2,"area":"safety"},{"id":"2509.21360","title":"Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models","created":"2025-09-21","cited_by_count":2,"area":"safety"},{"id":"2510.03263","title":"Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models","created":"2025-09-26","cited_by_count":2,"area":"safety"},{"id":"2512.14113","title":"Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach","created":"2025-12-16","cited_by_count":2,"area":"safety"},{"id":"2603.16489","title":"Unlearning for One-Step Generative Models via Unbalanced Optimal Transport","created":"2026-03-17","cited_by_count":2,"area":"safety"},{"id":"2604.12686","title":"BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning","created":"2026-04-14","cited_by_count":2,"area":"safety"},{"id":"2406.03603","title":"MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation","created":"2024-06-05","cited_by_count":1,"area":"safety"},{"id":"2411.16769","title":"Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting","created":"2024-11-25","cited_by_count":1,"area":"safety"},{"id":"2502.04260","title":"Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention","created":"2025-02-06","cited_by_count":1,"area":"safety"},{"id":"2503.15166","title":"Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU","created":"2025-03-19","cited_by_count":1,"area":"safety"},{"id":"2504.01218","title":"Prompting Forgetting: Unlearning in GANs via Textual Guidance","created":"2025-04-01","cited_by_count":1,"area":"safety"},{"id":"2504.14798","title":"RUB: Evaluating Residual Knowledge in Unlearned Models","created":"2025-04-21","cited_by_count":1,"area":"safety"},{"id":"2509.06277","title":"No Encore: Unlearning as Opt-Out in Music Generation","created":"2025-09-08","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":"2512.06562","title":"SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities","created":"2025-12-06","cited_by_count":1,"area":"safety"},{"id":"2602.09304","title":"Statistical Roughness-Informed Machine Unlearning","created":"2026-02-10","cited_by_count":1,"area":"safety"},{"id":"2603.11210","title":"Reference-Guided Machine Unlearning","created":"2026-03-11","cited_by_count":1,"area":"safety"},{"id":"2603.22870","title":"Designing to Forget: Deep Semi-parametric Models for Unlearning","created":"2026-03-24","cited_by_count":1,"area":"safety"},{"id":"2605.19227","title":"Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models","created":"2026-05-19","cited_by_count":1,"area":"safety"},{"id":"2605.25962","title":"Continual Speaker Identity Unlearning with Minimal Interference","created":"2026-05-25","cited_by_count":1,"area":"safety"},{"id":"2412.00067","title":"Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs","created":"2024-11-25","cited_by_count":0,"area":"safety"},{"id":"2506.04712","title":"UNO: Unlearning via Orthogonalization in Generative models","created":"2025-06-05","cited_by_count":0,"area":"safety"},{"id":"2506.11253","title":"Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models","created":"2025-06-12","cited_by_count":0,"area":"safety"},{"id":"2510.19226","title":"Controllable Machine Unlearning via Gradient Pivoting","created":"2025-10-22","cited_by_count":0,"area":"safety"},{"id":"2511.11014","title":"SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation","created":"2025-11-14","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":"2603.15679","title":"IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis","created":"2026-03-14","cited_by_count":0,"area":"safety"},{"id":"2603.16576","title":"REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.08111","title":"Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?","created":"2026-04-09","cited_by_count":0,"area":"safety"},{"id":"2604.09391","title":"Efficient Unlearning through Maximizing Relearning Convergence Delay","created":"2026-04-10","cited_by_count":0,"area":"safety"},{"id":"2604.15967","title":"When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models","created":"2026-04-17","cited_by_count":0,"area":"safety"},{"id":"2605.10680","title":"Behavioral Guarantees for Proxy-Based Unlearning","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.15737","title":"BARRIER: Bounded Activation Regions for Robust Information Erasure","created":"2026-05-15","cited_by_count":0,"area":"safety"},{"id":"2606.14351","title":"ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models","created":"2026-06-12","cited_by_count":0,"area":"safety"},{"id":"2606.17122","title":"TrustErase: Auditable Instant Machine Unlearning with Passport-Embedded Representations","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2606.29880","title":"IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation","created":"2026-06-29","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}