{"total":69,"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":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"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":"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":"2505.12677","title":"CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models","created":"2025-05-19","cited_by_count":27,"area":"diffusion"},{"id":"2507.13386","title":"Minimalist Concept Erasure in Generative Models","created":"2025-07-16","cited_by_count":13,"area":null},{"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":"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":"2511.07970","title":"Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective","created":"2025-11-11","cited_by_count":10,"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":"2411.02068","title":"Model Integrity when Unlearning with T2I Diffusion Models","created":"2024-11-04","cited_by_count":7,"area":"diffusion"},{"id":"2412.18123","title":"AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2502.12430","title":"Position: Bridge the Gaps between Machine Unlearning and AI Regulation","created":"2025-02-18","cited_by_count":7,"area":"safety"},{"id":"2503.13994","title":"TarPro: Targeted Protection against Malicious Image Editing","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2602.24041","title":"Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation","created":"2026-02-27","cited_by_count":7,"area":"mllm"},{"id":"2603.11493","title":"OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure","created":"2026-03-12","cited_by_count":7,"area":"mechinterp"},{"id":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7,"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":"2510.22124","title":"Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery","created":"2025-10-25","cited_by_count":5,"area":"safety"},{"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":"2501.03301","title":"Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective","created":"2025-01-06","cited_by_count":4,"area":null},{"id":"2504.02828","title":"Concept Lancet: Image Editing with Compositional Representation Transplant","created":"2025-04-03","cited_by_count":4,"area":"diffusion"},{"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":"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":"2509.11816","title":"Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning","created":"2025-09-15","cited_by_count":3,"area":"safety"},{"id":"2510.25739","title":"Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation","created":"2025-10-29","cited_by_count":3,"area":null},{"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":"2603.03163","title":"Conditioned Activation Transport for T2I Safety Steering","created":"2026-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2504.18563","title":"Backdoor Defense in Diffusion Models via Spatial Attention Unlearning","created":"2025-04-21","cited_by_count":2,"area":"diffusion"},{"id":"2508.18235","title":"Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation","created":"2025-08-20","cited_by_count":2,"area":"diffusion"},{"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":"2512.13953","title":"From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation","created":"2025-12-15","cited_by_count":2,"area":null},{"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":"2502.01472","title":"FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model","created":"2025-02-03","cited_by_count":1,"area":"alignment"},{"id":"2506.08991","title":"Do Concept Replacement Techniques Really Erase Unacceptable Concepts?","created":"2025-06-10","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":"2602.21773","title":"Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias","created":"2026-02-25","cited_by_count":1,"area":"safety"},{"id":"2604.00903","title":"IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off","created":"2026-04-01","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":"2412.18302","title":"FameBias: Embedding Manipulation Bias Attack in Text-to-Image Models","created":"2024-12-24","cited_by_count":0,"area":"diffusion"},{"id":"2502.15542","title":"Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations","created":"2025-02-21","cited_by_count":0,"area":"mllm"},{"id":"2508.11904","title":"SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress","created":"2025-08-16","cited_by_count":0,"area":"diffusion"},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2512.11194","title":"Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Training","created":"2025-12-12","cited_by_count":0,"area":"diffusion"},{"id":"2603.00975","title":"Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models","created":"2026-03-01","cited_by_count":0,"area":"diffusion"},{"id":"2603.00992","title":"Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information","created":"2026-03-01","cited_by_count":0,"area":"diffusion"},{"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":"2604.01514","title":"Why Instruction-Based Unlearning Fails in Diffusion Models?","created":"2026-04-02","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"},{"id":"2605.01113","title":"Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation","created":"2026-05-01","cited_by_count":0,"area":"diffusion"},{"id":"2605.18719","title":"SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training","created":"2026-05-18","cited_by_count":0,"area":"diffusion"},{"id":"2606.01658","title":"CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models","created":"2026-06-01","cited_by_count":0,"area":"diffusion"},{"id":"2606.02119","title":"How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning","created":"2026-06-01","cited_by_count":0,"area":"safety"},{"id":"2606.15819","title":"SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models","created":"2026-06-14","cited_by_count":0,"area":"alignment"},{"id":"2606.29880","title":"IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2607.08337","title":"AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate","created":"2026-07-09","cited_by_count":0,"area":"diffusion"},{"id":"2607.14194","title":"Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Models","created":"2026-07-15","cited_by_count":0,"area":"safety"},{"id":"2607.17779","title":"Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models","created":"2026-07-20","cited_by_count":0,"area":"safety"},{"id":"2607.24101","title":"LU-500: A Logo Benchmark for Concept Unlearning","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2609.09561","title":"Towards Automatic Evolution Tree Generation from Citation Graphs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.36832","title":"Motion Concept Unlearning in Video Diffusion Models","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.01989","title":"Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference","created":"2026-10-01","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}