{"total":133,"rows":[{"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":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"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":"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":"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":"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":"2502.08011","title":"Training-Free Safe Denoisers for Safe Use of Diffusion Models","created":"2025-02-11","cited_by_count":21,"area":"diffusion"},{"id":"2501.01633","title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models","created":"2025-01-03","cited_by_count":17,"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":"2505.17013","title":"When Are Concepts Erased From Diffusion Models?","created":"2025-05-22","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":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2412.02542","title":"Unveiling Concept Attribution in Diffusion Models","created":"2024-12-03","cited_by_count":11,"area":"diffusion"},{"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":"2601.21900","title":"TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention","created":"2026-01-29","cited_by_count":11,"area":"mechinterp"},{"id":"2602.20880","title":"When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance","created":"2026-02-24","cited_by_count":11,"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":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","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":"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":"2601.06162","title":"Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models","created":"2026-01-06","cited_by_count":9,"area":"diffusion"},{"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":"2510.22851","title":"Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models","created":"2025-10-26","cited_by_count":8,"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":"2510.24012","title":"Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models","created":"2025-10-28","cited_by_count":7,"area":"diffusion"},{"id":"2602.06258","title":"GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt","created":"2026-02-05","cited_by_count":7,"area":"alignment"},{"id":"2603.11493","title":"OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure","created":"2026-03-12","cited_by_count":7,"area":"mechinterp"},{"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":"2509.21433","title":"DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation","created":"2025-09-25","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":"2601.00590","title":"SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation","created":"2026-01-02","cited_by_count":6,"area":"safety"},{"id":"2603.13300","title":"Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation","created":"2026-03-02","cited_by_count":6,"area":null},{"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":"2512.02657","title":"Locality-Aware Continual Unlearning for Diffusion Models","created":"2025-12-02","cited_by_count":5,"area":"diffusion"},{"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":"2412.01339","title":"Negative Token Merging: Image-based Adversarial Feature Guidance","created":"2024-12-02","cited_by_count":4,"area":"diffusion"},{"id":"2412.07229","title":"Moderating the Generalization of Score-based Generative Model","created":"2024-12-10","cited_by_count":4,"area":"diffusion"},{"id":"2512.17320","title":"EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories","created":"2025-12-19","cited_by_count":4,"area":null},{"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":"2603.25994","title":"Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models","created":"2026-03-27","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":"2503.18674","title":"Human Motion Unlearning","created":"2025-03-24","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":"2602.19631","title":"Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection","created":"2026-02-23","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":"2502.17537","title":"Rethinking the Vulnerability of Concept Erasure and a New Method","created":"2025-02-24","cited_by_count":2,"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":"2505.06580","title":"TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification","created":"2025-05-10","cited_by_count":2,"area":null},{"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":"2511.12968","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":"2601.14330","title":"LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models","created":"2026-01-20","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":"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":"2503.16171","title":"Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation","created":"2025-03-19","cited_by_count":1,"area":null},{"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":"2507.13598","title":"GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention","created":"2025-07-18","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":"2602.00175","title":"The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization","created":"2026-01-30","cited_by_count":1,"area":"diffusion"},{"id":"2603.00978","title":"EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization","created":"2026-03-01","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":"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":"2605.10198","title":"Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models","created":"2026-05-11","cited_by_count":1,"area":"diffusion"},{"id":"2606.17257","title":"Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering","created":"2026-06-15","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":"2608.17747","title":"TINA+: Probing Residual Visual Knowledge in Unlearned Diffusion Models via Diffusion-Consistent Text-Free Inversion","created":"2026-08-18","cited_by_count":1,"area":"diffusion"},{"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":"2610.03980","title":"FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning","created":"2026-10-02","cited_by_count":1,"area":"diffusion"},{"id":"2610.05401","title":"No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models","created":"2026-10-04","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":"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":"2412.18302","title":"FameBias: Embedding Manipulation Bias Attack in Text-to-Image Models","created":"2024-12-24","cited_by_count":0,"area":"diffusion"},{"id":"2505.18672","title":"Concept Concentration for Faithful Representation Intervention","created":"2025-05-24","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":"2508.04472","title":"Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model","created":"2025-08-06","cited_by_count":0,"area":null},{"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":"2512.10720","title":"Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.13039","title":"Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models","created":"2025-12-15","cited_by_count":0,"area":"diffusion"},{"id":"2602.05339","title":"Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation","created":"2026-02-05","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}