{"total":264,"rows":[{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539,"area":"diffusion"},{"id":"2308.14761","title":"Unified Concept Editing in Diffusion Models","created":"2023-08-25","cited_by_count":388,"area":"diffusion"},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336,"area":null},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307,"area":"diffusion"},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273,"area":"mllm"},{"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":"2305.20086","title":"Understanding and Mitigating Copying in Diffusion Models","created":"2023-05-31","cited_by_count":209,"area":"diffusion"},{"id":"2311.17516","title":"MMA-Diffusion: MultiModal Attack on Diffusion Models","created":"2023-11-29","cited_by_count":194,"area":"diffusion"},{"id":"2305.12082","title":"SneakyPrompt: Jailbreaking Text-to-image Generative Models","created":"2023-05-20","cited_by_count":189,"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":"2312.16145","title":"One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications","created":"2023-12-26","cited_by_count":169,"area":"diffusion"},{"id":"2405.15234","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","created":"2024-05-24","cited_by_count":168,"area":"diffusion"},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2407.12383","title":"Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models","created":"2024-07-17","cited_by_count":133,"area":"diffusion"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95,"area":"diffusion"},{"id":"2308.01508","title":"Circumventing Concept Erasure Methods For Text-to-Image Generative Models","created":"2023-08-03","cited_by_count":85,"area":null},{"id":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83,"area":"safety"},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83,"area":"safety"},{"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":"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":"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":"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":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66,"area":null},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63,"area":null},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62,"area":"safety"},{"id":"2405.16341","title":"R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model","created":"2024-05-25","cited_by_count":58,"area":"diffusion"},{"id":"2211.14946","title":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","created":"2022-11-27","cited_by_count":57,"area":null},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53,"area":"wm"},{"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":"2501.04931","title":"Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency","created":"2025-01-09","cited_by_count":51,"area":"mllm"},{"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":"2410.15618","title":"Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation","created":"2024-10-21","cited_by_count":50,"area":"diffusion"},{"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":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45,"area":"safety"},{"id":"2408.16807","title":"STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models","created":"2024-08-29","cited_by_count":42,"area":"diffusion"},{"id":"2408.10848","title":"Perception-guided Jailbreak against Text-to-Image Models","created":"2024-08-20","cited_by_count":40,"area":"safety"},{"id":"2410.12777","title":"Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts","created":"2024-10-16","cited_by_count":40,"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":"2411.15720","title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","created":"2024-11-24","cited_by_count":39,"area":"mllm"},{"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":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"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":"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":"2312.12807","title":"All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models","created":"2023-12-20","cited_by_count":33,"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":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"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":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2402.10882","title":"Universal Prompt Optimizer for Safe Text-to-Image Generation","created":"2024-02-16","cited_by_count":28,"area":null},{"id":"2308.02552","title":"Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion","created":"2023-08-02","cited_by_count":27,"area":"diffusion"},{"id":"2404.03631","title":"Robust Concept Erasure Using Task Vectors","created":"2024-04-04","cited_by_count":27,"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":"2406.14194","title":"VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model","created":"2024-06-20","cited_by_count":26,"area":"mllm"},{"id":"2409.11219","title":"Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models","created":"2024-09-17","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":"2405.16534","title":"Pruning for Robust Concept Erasing in Diffusion Models","created":"2024-05-26","cited_by_count":22,"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":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"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":"2403.12075","title":"Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation","created":"2024-02-14","cited_by_count":20,"area":"safety"},{"id":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2311.18815","title":"IMMA: Immunizing text-to-image Models against Malicious Adaptation","created":"2023-11-30","cited_by_count":18,"area":null},{"id":"2503.12127","title":"Hyperbolic Safety-Aware Vision-Language Models","created":"2025-03-15","cited_by_count":17,"area":"mllm"},{"id":"2306.06135","title":"Safety and Fairness for Content Moderation in Generative Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2412.15341","title":"Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models","created":"2024-12-19","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":"2402.01787","title":"Harm Amplification in Text-to-Image Models","created":"2024-02-01","cited_by_count":15,"area":null},{"id":"2408.07728","title":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies","created":"2024-08-14","cited_by_count":15,"area":"diffusion"},{"id":"2410.04772","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","created":"2024-10-07","cited_by_count":15,"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":"2410.09140","title":"RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining","created":"2024-10-11","cited_by_count":15,"area":null},{"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":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2601.03305","title":"Mass Concept Erasure in Diffusion Models with Concept Hierarchy","created":"2026-01-06","cited_by_count":14,"area":"diffusion"},{"id":"2403.02580","title":"What do we learn from inverting CLIP models?","created":"2024-03-05","cited_by_count":13,"area":null},{"id":"2404.19382","title":"Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective","created":"2024-04-30","cited_by_count":13,"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":"2508.15124","title":"Side Effects of Erasing Concepts from Diffusion Models","created":"2025-08-20","cited_by_count":13,"area":"diffusion"},{"id":"2404.13706","title":"Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models","created":"2024-04-21","cited_by_count":12,"area":"diffusion"},{"id":"2405.11336","title":"UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers","created":"2024-05-18","cited_by_count":12,"area":null},{"id":"2407.15328","title":"Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models","created":"2024-07-22","cited_by_count":12,"area":"diffusion"},{"id":"2408.01014","title":"Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models","created":"2024-08-02","cited_by_count":12,"area":"diffusion"},{"id":"2503.13769","title":"Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion","created":"2025-03-17","cited_by_count":12,"area":"safety"},{"id":"2307.10711","title":"AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models","created":"2023-07-20","cited_by_count":11,"area":"diffusion"},{"id":"2408.00001","title":"Replication in Visual Diffusion Models: A Survey and Outlook","created":"2024-07-07","cited_by_count":11,"area":"diffusion"},{"id":"2412.01244","title":"Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization","created":"2024-12-02","cited_by_count":11,"area":"diffusion"},{"id":"2501.01125","title":"DuMo: Dual Encoder Modulation Network for Precise Concept Erasure","created":"2025-01-02","cited_by_count":11,"area":null}],"next_cursor":"100"}