{"total":120,"rows":[{"id":"2405.15234","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","created":"2024-05-24","cited_by_count":168,"area":"diffusion"},{"id":"2410.12761","title":"SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation","created":"2024-10-16","cited_by_count":133,"area":"diffusion"},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95,"area":"diffusion"},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62,"area":null},{"id":"2405.16341","title":"R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model","created":"2024-05-25","cited_by_count":58,"area":"diffusion"},{"id":"2405.19237","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","created":"2024-05-29","cited_by_count":55,"area":"diffusion"},{"id":"2402.11846","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","created":"2024-02-19","cited_by_count":50,"area":"diffusion"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2408.16807","title":"STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models","created":"2024-08-29","cited_by_count":42,"area":"diffusion"},{"id":"2410.12777","title":"Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts","created":"2024-10-16","cited_by_count":40,"area":"diffusion"},{"id":"2503.07392","title":"SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models","created":"2025-03-10","cited_by_count":36,"area":"diffusion"},{"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":"2407.15861","title":"Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey","created":"2024-07-10","cited_by_count":35,"area":"diffusion"},{"id":"2503.12356","title":"Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation","created":"2025-03-16","cited_by_count":33,"area":"diffusion"},{"id":"2408.03400","title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","created":"2024-08-06","cited_by_count":32,"area":"diffusion"},{"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":"2405.07288","title":"Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning","created":"2024-05-12","cited_by_count":29,"area":"diffusion"},{"id":"2402.05947","title":"Separable Multi-Concept Erasure from Diffusion Models","created":"2024-02-03","cited_by_count":28,"area":"diffusion"},{"id":"2505.12677","title":"CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models","created":"2025-05-19","cited_by_count":27,"area":"diffusion"},{"id":"2412.07658","title":"TraSCE: Trajectory Steering for Concept Erasure","created":"2024-12-10","cited_by_count":26,"area":"diffusion"},{"id":"2503.19783","title":"Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models","created":"2025-03-25","cited_by_count":25,"area":"diffusion"},{"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":"2410.05664","title":"Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning","created":"2024-10-08","cited_by_count":21,"area":"diffusion"},{"id":"2503.21781","title":"VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models","created":"2025-03-27","cited_by_count":17,"area":"diffusion"},{"id":"2412.15341","title":"Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models","created":"2024-12-19","cited_by_count":16,"area":"diffusion"},{"id":"2505.11131","title":"One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework","created":"2025-05-16","cited_by_count":16,"area":"diffusion"},{"id":"2505.17550","title":"T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models","created":"2025-05-23","cited_by_count":16,"area":"diffusion"},{"id":"2506.22806","title":"Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate","created":"2025-06-28","cited_by_count":16,"area":"diffusion"},{"id":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2601.03305","title":"Mass Concept Erasure in Diffusion Models with Concept Hierarchy","created":"2026-01-06","cited_by_count":14,"area":"diffusion"},{"id":"2508.15124","title":"Side Effects of Erasing Concepts from Diffusion Models","created":"2025-08-20","cited_by_count":13,"area":"diffusion"},{"id":"2501.09833","title":"Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2408.00001","title":"Replication in Visual Diffusion Models: A Survey and Outlook","created":"2024-07-07","cited_by_count":11,"area":"diffusion"},{"id":"2501.01125","title":"DuMo: Dual Encoder Modulation Network for Precise Concept Erasure","created":"2025-01-02","cited_by_count":11,"area":null},{"id":"2502.16368","title":"Concept Corrector: Erase concepts on the fly for text-to-image diffusion models","created":"2025-02-22","cited_by_count":11,"area":"diffusion"},{"id":"2410.02710","title":"SteerDiff: Steering towards Safe Text-to-Image Diffusion Models","created":"2024-10-03","cited_by_count":10,"area":"diffusion"},{"id":"2505.19398","title":"Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2507.07139","title":"Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning","created":"2025-07-09","cited_by_count":10,"area":"diffusion"},{"id":"2509.21379","title":"SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders","created":"2025-09-23","cited_by_count":10,"area":"diffusion"},{"id":"2411.18289","title":"Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy","created":"2024-11-27","cited_by_count":9,"area":null},{"id":"2502.14896","title":"A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models","created":"2025-02-17","cited_by_count":9,"area":"diffusion"},{"id":"2504.21072","title":"Erased but Not Forgotten: How Backdoors Compromise Concept Erasure","created":"2025-04-29","cited_by_count":9,"area":"diffusion"},{"id":"2505.16174","title":"Erased or Dormant? Rethinking Concept Erasure Through Reversibility","created":"2025-05-22","cited_by_count":9,"area":"diffusion"},{"id":"2506.02761","title":"Rethinking Machine Unlearning in Image Generation Models","created":"2025-06-03","cited_by_count":9,"area":"safety"},{"id":"2507.16302","title":"Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning","created":"2025-07-22","cited_by_count":9,"area":"diffusion"},{"id":"2511.00804","title":"EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment","created":"2025-11-02","cited_by_count":9,"area":"alignment"},{"id":"2501.15562","title":"CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary","created":"2025-01-26","cited_by_count":8,"area":"diffusion"},{"id":"2503.09446","title":"Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models","created":"2025-03-12","cited_by_count":8,"area":"diffusion"},{"id":"2510.22851","title":"Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models","created":"2025-10-26","cited_by_count":8,"area":"diffusion"},{"id":"2501.00054","title":"AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors","created":"2024-12-28","cited_by_count":7,"area":"diffusion"},{"id":"2501.19066","title":"Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2503.13994","title":"TarPro: Targeted Protection against Malicious Image Editing","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2603.11493","title":"OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure","created":"2026-03-12","cited_by_count":7,"area":"mechinterp"},{"id":"2503.08116","title":"ACE: Concept Editing in Diffusion Models without Performance Degradation","created":"2025-03-11","cited_by_count":6,"area":"diffusion"},{"id":"2503.14232","title":"CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models","created":"2025-03-18","cited_by_count":6,"area":"diffusion"},{"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":"2503.18324","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2512.02657","title":"Locality-Aware Continual Unlearning for Diffusion Models","created":"2025-12-02","cited_by_count":5,"area":"diffusion"},{"id":"2512.23546","title":"PurifyGen: A Risk-Discrimination and Semantic-Purification Model for Safe Text-to-Image Generation","created":"2025-12-29","cited_by_count":5,"area":"diffusion"},{"id":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","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":"2504.11850","title":"ACE: Attentional Concept Erasure in Diffusion Models","created":"2025-04-16","cited_by_count":3,"area":"diffusion"},{"id":"2508.00591","title":"Wukong Framework for Not Safe For Work Detection in Text-to-Image systems","created":"2025-08-01","cited_by_count":3,"area":"diffusion"},{"id":"2509.15257","title":"RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation","created":"2025-09-18","cited_by_count":3,"area":"diffusion"},{"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":"2604.10032","title":"Closed-Form Concept Erasure via Double Projections","created":"2026-04-11","cited_by_count":3,"area":"diffusion"},{"id":"2607.23492","title":"To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion","created":"2026-07-26","cited_by_count":3,"area":"diffusion"},{"id":"2504.21307","title":"The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models","created":"2025-04-30","cited_by_count":2,"area":"diffusion"},{"id":"2509.16986","title":"VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2509.21167","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","created":"2025-09-25","cited_by_count":2,"area":"diffusion"},{"id":"2511.11693","title":"Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image Generation","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2511.12968","title":"GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models","created":"2025-11-17","cited_by_count":2,"area":"diffusion"},{"id":"2512.22877","title":"M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models","created":"2025-12-28","cited_by_count":2,"area":"diffusion"},{"id":"2606.05290","title":"Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2411.13982","title":"Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction","created":"2024-11-21","cited_by_count":1,"area":null},{"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":"2506.09363","title":"SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing","created":"2025-06-11","cited_by_count":1,"area":"diffusion"},{"id":"2507.07137","title":"Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge","created":"2025-07-09","cited_by_count":1,"area":"diffusion"},{"id":"2510.15752","title":"NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation","created":"2025-10-17","cited_by_count":1,"area":"diffusion"},{"id":"2510.16342","title":"Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts","created":"2025-10-18","cited_by_count":1,"area":"diffusion"},{"id":"2510.27285","title":"Rethinking Robust Adversarial Concept Erasure in Diffusion Models","created":"2025-10-31","cited_by_count":1,"area":"diffusion"},{"id":"2601.03213","title":"Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion","created":"2026-01-06","cited_by_count":1,"area":"diffusion"},{"id":"2603.08271","title":"Prototype-Guided Concept Erasure in Diffusion Models","created":"2026-03-09","cited_by_count":1,"area":"diffusion"},{"id":"2603.10445","title":"Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models","created":"2026-03-11","cited_by_count":1,"area":"diffusion"},{"id":"2603.21547","title":"PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models","created":"2026-03-23","cited_by_count":1,"area":"diffusion"},{"id":"2604.04575","title":"Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models","created":"2026-04-06","cited_by_count":1,"area":"diffusion"},{"id":"2604.09405","title":"EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure","created":"2026-04-10","cited_by_count":1,"area":"diffusion"},{"id":"2604.15829","title":"Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.25119","title":"Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.26332","title":"Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2606.28643","title":"Obliviate: Erasing Concepts from Autoregressive Image Generation Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2610.01969","title":"RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models","created":"2026-10-01","cited_by_count":1,"area":"diffusion"},{"id":"2610.05601","title":"Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models","created":"2026-10-04","cited_by_count":1,"area":"diffusion"},{"id":"2405.17069","title":"Training-free Editioning of Text-to-Image Models","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2409.17682","title":"Dark Miner: Defend against undesirable generation for text-to-image diffusion models","created":"2024-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2410.04447","title":"Attention Shift: Steering AI Away from Unsafe Content","created":"2024-10-06","cited_by_count":0,"area":"safety"},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2602.08059","title":"DICE: Disentangling Artist Style from Content via Contrastive Subspace Decomposition in Diffusion Models","created":"2026-02-08","cited_by_count":0,"area":"diffusion"},{"id":"2603.18767","title":"A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models","created":"2026-03-19","cited_by_count":0,"area":"diffusion"},{"id":"2604.21041","title":"Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks","created":"2026-04-22","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}