{"total":64,"rows":[{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513,"area":"diffusion"},{"id":"2310.10012","title":"Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?","created":"2023-10-16","cited_by_count":250,"area":"diffusion"},{"id":"2310.11868","title":"To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now","created":"2023-10-18","cited_by_count":210,"area":"diffusion"},{"id":"2311.17516","title":"MMA-Diffusion: MultiModal Attack on Diffusion Models","created":"2023-11-29","cited_by_count":194,"area":"diffusion"},{"id":"2305.13873","title":"Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models","created":"2023-05-23","cited_by_count":175,"area":"diffusion"},{"id":"2309.06135","title":"Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts","created":"2023-09-12","cited_by_count":171,"area":"diffusion"},{"id":"2311.17717","title":"Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers","created":"2023-11-29","cited_by_count":120,"area":"diffusion"},{"id":"2404.02928","title":"Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models","created":"2024-04-02","cited_by_count":72,"area":"diffusion"},{"id":"2311.17216","title":"Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation","created":"2023-11-28","cited_by_count":69,"area":"diffusion"},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2307.05977","title":"Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models","created":"2023-07-12","cited_by_count":41,"area":"diffusion"},{"id":"2412.06143","title":"Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters","created":"2024-12-09","cited_by_count":40,"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":"2310.05873","title":"Implicit Concept Removal of Diffusion Models","created":"2023-10-09","cited_by_count":23,"area":"diffusion"},{"id":"2408.11071","title":"DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization","created":"2024-08-18","cited_by_count":22,"area":"diffusion"},{"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":"2502.08011","title":"Training-Free Safe Denoisers for Safe Use of Diffusion Models","created":"2025-02-11","cited_by_count":21,"area":"diffusion"},{"id":"2505.06679","title":"T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks","created":"2025-05-10","cited_by_count":21,"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":"2409.19149","title":"Multimodal Pragmatic Jailbreak on Text-to-image Models","created":"2024-09-27","cited_by_count":13,"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":"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":"2510.03302","title":"Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models","created":"2025-09-30","cited_by_count":11,"area":"diffusion"},{"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":"2410.02710","title":"SteerDiff: Steering towards Safe Text-to-Image Diffusion Models","created":"2024-10-03","cited_by_count":10,"area":"diffusion"},{"id":"2410.21471","title":"AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models","created":"2024-10-28","cited_by_count":10,"area":"diffusion"},{"id":"2412.00064","title":"DiffGuard: Text-Based Safety Checker for Diffusion Models","created":"2024-11-25","cited_by_count":10,"area":"diffusion"},{"id":"2505.15427","title":"Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions","created":"2025-05-21","cited_by_count":8,"area":"diffusion"},{"id":"2509.21008","title":"A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models","created":"2025-09-25","cited_by_count":8,"area":"diffusion"},{"id":"2408.17285","title":"Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution","created":"2024-08-30","cited_by_count":7,"area":"diffusion"},{"id":"2412.03876","title":"Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization","created":"2024-12-05","cited_by_count":7,"area":"diffusion"},{"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":"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":"2507.22617","title":"Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions","created":"2025-07-30","cited_by_count":6,"area":"diffusion"},{"id":"2503.08455","title":"Controlling Latent Diffusion Using Latent CLIP","created":"2025-03-11","cited_by_count":4,"area":"diffusion"},{"id":"2601.00267","title":"ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection","created":"2026-01-01","cited_by_count":4,"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":"2510.00635","title":"Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack","created":"2025-10-01","cited_by_count":3,"area":"diffusion"},{"id":"2603.21208","title":"JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization","created":"2026-03-22","cited_by_count":3,"area":"diffusion"},{"id":"2412.16039","title":"SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation","created":"2024-12-20","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":"2606.00140","title":"GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows","created":"2026-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2501.05359","title":"SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack","created":"2025-01-09","cited_by_count":1,"area":"diffusion"},{"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":"2508.01151","title":"Personalized Safety Alignment for Text-to-Image Diffusion Models","created":"2025-08-02","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":"2511.04834","title":"Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models","created":"2025-11-06","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":"2603.08271","title":"Prototype-Guided Concept Erasure in Diffusion Models","created":"2026-03-09","cited_by_count":1,"area":"diffusion"},{"id":"2606.23267","title":"Safe Few-Step Generation via Velocity Editing","created":"2026-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2607.00402","title":"The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models","created":"2026-07-01","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":"2402.04699","title":"Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!","created":"2024-02-07","cited_by_count":0,"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":"2505.08817","title":"Towards SFW sampling for diffusion models via external conditioning","created":"2025-05-12","cited_by_count":0,"area":"diffusion"},{"id":"2510.26105","title":"Security Risk of Misalignment between Text and Image in Multi-modal Model","created":"2025-10-30","cited_by_count":0,"area":"diffusion"},{"id":"2602.00616","title":"SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation","created":"2026-01-31","cited_by_count":0,"area":"diffusion"},{"id":"2605.25765","title":"Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models","created":"2026-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2605.30049","title":"Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers","created":"2026-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2606.29801","title":"Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2609.33445","title":"Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2610.19563","title":"SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization","created":"2026-10-14","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}