{"total":62,"rows":[{"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":"2404.06666","title":"SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models","created":"2024-04-10","cited_by_count":66,"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":"2501.18950","title":"Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them","created":"2025-01-31","cited_by_count":37,"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":"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":"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":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2412.02542","title":"Unveiling Concept Attribution in Diffusion Models","created":"2024-12-03","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":"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":"2403.12326","title":"Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts","created":"2024-03-18","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":"2410.05309","title":"ShieldDiff: Suppressing Sexual Content Generation from Diffusion Models through Reinforcement Learning","created":"2024-10-04","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":"2512.23953","title":"T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models","created":"2025-12-30","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":"2506.10047","title":"GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models","created":"2025-06-11","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":"2508.03006","title":"Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models","created":"2025-08-05","cited_by_count":3,"area":"diffusion"},{"id":"2509.22723","title":"Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models","created":"2025-09-25","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":"2606.01481","title":"SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation","created":"2026-05-31","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":"2508.06837","title":"Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models","created":"2025-08-09","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":"2604.07879","title":"FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding","created":"2026-04-09","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":"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":"2507.07947","title":"Reconstructing Template-Memorized Images from Natural Prompts","created":"2025-07-10","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":"2510.15752","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":"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":"2603.22041","title":"DTVI: Dual-Stage Textual and Visual Intervention for Safe Text-to-Image Generation","created":"2026-03-23","cited_by_count":1,"area":"diffusion"},{"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":"2606.17257","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":"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":"2502.05066","title":"Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images","created":"2025-02-07","cited_by_count":0,"area":"diffusion"},{"id":"2511.21180","title":"CAHS-Attack: CLIP-Aware Heuristic Search Attack Method for Stable Diffusion","created":"2025-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2512.08724","title":"Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search","created":"2025-12-09","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":"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":"2605.01113","title":"Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation","created":"2026-05-01","cited_by_count":0,"area":"diffusion"},{"id":"2605.30049","title":"Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers","created":"2026-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2607.06120","title":"AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models","created":"2026-07-07","cited_by_count":0,"area":"diffusion"},{"id":"2607.16828","title":"UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation","created":"2026-07-18","cited_by_count":0,"area":"diffusion"},{"id":"2608.15341","title":"TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models","created":"2026-08-15","cited_by_count":0,"area":"diffusion"},{"id":"2608.21869","title":"GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration","created":"2026-08-22","cited_by_count":0,"area":"diffusion"},{"id":"2609.05503","title":"A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities","created":"2026-08-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.36832","title":"Motion Concept Unlearning in Video Diffusion Models","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.18990","title":"Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models","created":"2026-10-13","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}