{"total":155,"rows":[{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152,"area":null},{"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":"2302.10893","title":"Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness","created":"2023-02-07","cited_by_count":151,"area":null},{"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":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83,"area":"safety"},{"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":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71,"area":null},{"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":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2405.03486","title":"UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images","created":"2024-05-06","cited_by_count":53,"area":null},{"id":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52,"area":"safety"},{"id":"2406.05113","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","created":"2024-06-07","cited_by_count":52,"area":"safety"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2501.12612","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation","created":"2025-01-22","cited_by_count":48,"area":null},{"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":"2405.19360","title":"ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users","created":"2024-05-24","cited_by_count":35,"area":"safety"},{"id":"2309.14122","title":"SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution","created":"2023-09-25","cited_by_count":34,"area":null},{"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":"2402.10882","title":"Universal Prompt Optimizer for Safe Text-to-Image Generation","created":"2024-02-16","cited_by_count":28,"area":null},{"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":"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":"2501.00192","title":"MLLM-as-a-Judge for Image Safety without Human Labeling","created":"2024-12-31","cited_by_count":23,"area":null},{"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":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2209.07341","title":"Does CLIP Know My Face?","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2503.12127","title":"Hyperbolic Safety-Aware Vision-Language Models","created":"2025-03-15","cited_by_count":17,"area":"mllm"},{"id":"2510.22300","title":"T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model","created":"2025-10-25","cited_by_count":17,"area":null},{"id":"2305.18398","title":"Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?","created":"2023-05-28","cited_by_count":16,"area":null},{"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":"2311.16254","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2409.19734","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","created":"2024-09-29","cited_by_count":11,"area":"safety"},{"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":"2504.11106","title":"Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models","created":"2025-04-15","cited_by_count":9,"area":"safety"},{"id":"2506.02761","title":"Rethinking Machine Unlearning in Image Generation Models","created":"2025-06-03","cited_by_count":9,"area":"safety"},{"id":"2508.03696","title":"PLA: Prompt Learning Attack against Text-to-Image Generative Models","created":"2025-07-14","cited_by_count":9,"area":"safety"},{"id":"2210.10332","title":"Revision Transformers: Instructing Language Models to Change their Values","created":"2022-10-19","cited_by_count":8,"area":null},{"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":"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":"2509.21008","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":"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":"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":"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":"2602.20999","title":"VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models","created":"2026-02-24","cited_by_count":7,"area":"safety"},{"id":"2603.11493","title":"OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure","created":"2026-03-12","cited_by_count":7,"area":"mechinterp"},{"id":"2309.11575","title":"Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge","created":"2023-09-20","cited_by_count":6,"area":"safety"},{"id":"2504.11707","title":"Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset","created":"2025-04-16","cited_by_count":6,"area":null},{"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":"2509.13760","title":"Iterative Prompt Refinement for Safer Text-to-Image Generation","created":"2025-09-17","cited_by_count":6,"area":"mllm"},{"id":"2510.05173","title":"SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models","created":"2025-10-05","cited_by_count":6,"area":"safety"},{"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":"2603.01228","title":"Towards Policy-Adaptive Image Guardrail: Benchmark and Method","created":"2026-03-01","cited_by_count":6,"area":"safety"},{"id":"2208.08241","title":"ILLUME: Rationalizing Vision-Language Models through Human Interactions","created":"2022-08-17","cited_by_count":5,"area":"mllm"},{"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":"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":"2504.20376","title":"When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems","created":"2025-04-29","cited_by_count":5,"area":"safety"},{"id":"2505.18979","title":"Dynamic Optimization and Safety Indicator Injection for Jailbreaking Text-to-Image Models with Multimodal Safety Filters","created":"2025-05-25","cited_by_count":5,"area":"safety"},{"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":"2604.01888","title":"Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters","created":"2026-04-02","cited_by_count":5,"area":"safety"},{"id":"2411.10329","title":"Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2503.08455","title":"Controlling Latent Diffusion Using Latent CLIP","created":"2025-03-11","cited_by_count":4,"area":"diffusion"},{"id":"2506.22557","title":"MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs","created":"2025-06-27","cited_by_count":4,"area":"agents"},{"id":"2510.23960","title":"SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability","created":"2025-10-28","cited_by_count":4,"area":"safety"},{"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":"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":"2309.09944","title":"DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2407.19180","title":"Data Processing Techniques for Modern Multimodal Models","created":"2024-07-27","cited_by_count":3,"area":null},{"id":"2412.07249","title":"Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation","created":"2024-12-10","cited_by_count":3,"area":"safety"},{"id":"2412.08156","title":"Antelope: Potent and Concealed Jailbreak Attack Strategy","created":"2024-12-11","cited_by_count":3,"area":"safety"},{"id":"2503.13463","title":"Completeness of Datasets Documentation on ML/AI repositories: an Empirical Investigation","created":"2025-02-10","cited_by_count":3,"area":null},{"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":"2511.16743","title":"SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge","created":"2025-11-20","cited_by_count":3,"area":"mllm"},{"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":"2606.15608","title":"On the Adversarial Robustness of Multimodal LLM Judges","created":"2026-06-14","cited_by_count":3,"area":"mllm"},{"id":"2409.17216","title":"Data-Centric AI Governance: Addressing the Limitations of Model-Focused Policies","created":"2024-09-25","cited_by_count":2,"area":null}],"next_cursor":"100"}