{"total":168,"rows":[{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95,"area":"diffusion"},{"id":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"area":"diffusion"},{"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":"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":"2405.19237","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","created":"2024-05-29","cited_by_count":55,"area":"diffusion"},{"id":"2410.15618","title":"Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation","created":"2024-10-21","cited_by_count":50,"area":"diffusion"},{"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":"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":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2408.00523","title":"Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models","created":"2024-08-01","cited_by_count":27,"area":"agents"},{"id":"2412.07658","title":"TraSCE: Trajectory Steering for Concept Erasure","created":"2024-12-10","cited_by_count":26,"area":"diffusion"},{"id":"2409.11219","title":"Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models","created":"2024-09-17","cited_by_count":23,"area":"diffusion"},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2411.16832","title":"Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing","created":"2024-11-25","cited_by_count":21,"area":"diffusion"},{"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":"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":"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":"2410.08074","title":"Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models","created":"2024-10-10","cited_by_count":15,"area":"diffusion"},{"id":"2503.07389","title":"TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models","created":"2025-03-10","cited_by_count":15,"area":"diffusion"},{"id":"2503.15197","title":"Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization","created":"2025-03-19","cited_by_count":13,"area":"diffusion"},{"id":"2507.13386","title":"Minimalist Concept Erasure in Generative Models","created":"2025-07-16","cited_by_count":13,"area":null},{"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":"2411.13632","title":"ID-Patch: Robust ID Association for Group Photo Personalization","created":"2024-11-20","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":"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":"2410.02710","title":"SteerDiff: Steering towards Safe Text-to-Image Diffusion Models","created":"2024-10-03","cited_by_count":10,"area":"diffusion"},{"id":"2412.00782","title":"Memories of Forgotten Concepts","created":"2024-12-01","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":"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":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8,"area":null},{"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":"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":"2509.05625","title":"SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models","created":"2025-09-06","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":"2411.02068","title":"Model Integrity when Unlearning with T2I Diffusion Models","created":"2024-11-04","cited_by_count":7,"area":"diffusion"},{"id":"2412.05538","title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2501.18877","title":"Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models","created":"2025-01-31","cited_by_count":7,"area":"diffusion"},{"id":"2502.20623","title":"SafeText: Safe Text-to-image Models via Aligning the Text Encoder","created":"2025-02-28","cited_by_count":7,"area":null},{"id":"2503.13994","title":"TarPro: Targeted Protection against Malicious Image Editing","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2412.00580","title":"Continuous Concepts Removal in Text-to-image Diffusion Models","created":"2024-11-30","cited_by_count":6,"area":"diffusion"},{"id":"2412.16780","title":"Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification","created":"2024-12-21","cited_by_count":6,"area":"safety"},{"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":"2406.16810","title":"How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective","created":"2024-06-24","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":"2507.06526","title":"Concept Unlearning by Modeling Key Steps of Diffusion Process","created":"2025-07-09","cited_by_count":5,"area":"diffusion"},{"id":"2507.16329","title":"DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling","created":"2025-07-22","cited_by_count":5,"area":"alignment"},{"id":"2508.05658","title":"Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards","created":"2025-07-30","cited_by_count":5,"area":"safety"},{"id":"2602.06771","title":"AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models","created":"2026-02-06","cited_by_count":5,"area":"diffusion"},{"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":"2506.20151","title":"EAR: Erasing Concepts from Unified Autoregressive Models","created":"2025-06-25","cited_by_count":4,"area":null},{"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":"2603.17828","title":"TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models","created":"2026-03-18","cited_by_count":4,"area":"diffusion"},{"id":"2606.24192","title":"Co-occurring Associated REtained concepts in Diffusion Unlearning","created":"2026-06-23","cited_by_count":4,"area":"diffusion"},{"id":"2504.11850","title":"ACE: Attentional Concept Erasure in Diffusion Models","created":"2025-04-16","cited_by_count":3,"area":"diffusion"},{"id":"2506.18747","title":"ContinualFlow: Learning and Unlearning with Neural Flow Matching","created":"2025-06-23","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":"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":"2602.03410","title":"UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning","created":"2026-02-03","cited_by_count":3,"area":"diffusion"},{"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":"2410.14975","title":"Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation","created":"2024-10-19","cited_by_count":2,"area":"mllm"},{"id":"2502.17537","title":"Rethinking the Vulnerability of Concept Erasure and a New Method","created":"2025-02-24","cited_by_count":2,"area":"diffusion"},{"id":"2503.00917","title":"AMUN: Adversarial Machine UNlearning","created":"2025-03-02","cited_by_count":2,"area":"safety"},{"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":"2507.21985","title":"ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models","created":"2025-07-29","cited_by_count":2,"area":"safety"},{"id":"2509.16986","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":"2510.03263","title":"Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models","created":"2025-09-26","cited_by_count":2,"area":"safety"},{"id":"2511.11299","title":"AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models","created":"2025-11-14","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":"2511.19558","title":"SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation","created":"2025-11-24","cited_by_count":2,"area":"diffusion"},{"id":"2602.07919","title":"Selective Fine-Tuning for Targeted and Robust Concept Unlearning","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2604.01826","title":"SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers","created":"2026-04-02","cited_by_count":2,"area":"diffusion"},{"id":"2605.28902","title":"Orthogonal Concept Erasure for Diffusion Models","created":"2026-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2605.30825","title":"Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints","created":"2026-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2606.00140","title":"GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows","created":"2026-05-29","cited_by_count":2,"area":"diffusion"},{"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":"2504.14798","title":"RUB: Evaluating Residual Knowledge in Unlearned Models","created":"2025-04-21","cited_by_count":1,"area":"safety"},{"id":"2505.15450","title":"Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models","created":"2025-05-21","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}