{"total":171,"rows":[{"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":"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":"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":"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":"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":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","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":"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":"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":"2402.11846","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","created":"2024-02-19","cited_by_count":50,"area":"diffusion"},{"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":"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":"2405.20112","title":"RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection","created":"2024-05-30","cited_by_count":36,"area":null},{"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":"2402.05947","title":"Separable Multi-Concept Erasure from Diffusion Models","created":"2024-02-03","cited_by_count":28,"area":"diffusion"},{"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":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25,"area":"safety"},{"id":"2406.14526","title":"Fantastic Copyrighted Beasts and How (Not) to Generate Them","created":"2024-06-20","cited_by_count":24,"area":null},{"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":"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":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2505.11131","title":"One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework","created":"2025-05-16","cited_by_count":16,"area":"diffusion"},{"id":"2505.17013","title":"When Are Concepts Erased From Diffusion Models?","created":"2025-05-22","cited_by_count":16,"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":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2508.15314","title":"VideoEraser: Concept Erasure in Text-to-Video Diffusion Models","created":"2025-08-21","cited_by_count":14,"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":"2507.13386","title":"Minimalist Concept Erasure in Generative Models","created":"2025-07-16","cited_by_count":13,"area":null},{"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":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2412.02542","title":"Unveiling Concept Attribution in Diffusion Models","created":"2024-12-03","cited_by_count":11,"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":"2601.21900","title":"TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention","created":"2026-01-29","cited_by_count":11,"area":"mechinterp"},{"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":"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":"2407.17447","title":"FLRT: Fluent Student-Teacher Redteaming","created":"2024-07-24","cited_by_count":9,"area":"safety"},{"id":"2502.14896","title":"A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models","created":"2025-02-17","cited_by_count":9,"area":"diffusion"},{"id":"2504.21072","title":"Erased but Not Forgotten: How Backdoors Compromise Concept Erasure","created":"2025-04-29","cited_by_count":9,"area":"diffusion"},{"id":"2511.00804","title":"EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment","created":"2025-11-02","cited_by_count":9,"area":"alignment"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2405.03654","title":"Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent","created":"2024-05-06","cited_by_count":8,"area":"safety"},{"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":"2502.16618","title":"Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"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":"2509.05625","title":"SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models","created":"2025-09-06","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":"2412.18123","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":"2501.00054","title":"AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors","created":"2024-12-28","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":"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":"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":"2412.00580","title":"Continuous Concepts Removal in Text-to-image Diffusion Models","created":"2024-11-30","cited_by_count":6,"area":"diffusion"},{"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":"2601.13578","title":"FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning","created":"2026-01-20","cited_by_count":6,"area":"safety"},{"id":"2312.00057","title":"VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2410.14881","title":"Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation","created":"2024-10-18","cited_by_count":5,"area":"rag"},{"id":"2507.06526","title":"Concept Unlearning by Modeling Key Steps of Diffusion Process","created":"2025-07-09","cited_by_count":5,"area":"diffusion"},{"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":"2602.01089","title":"Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models","created":"2026-02-01","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":"2412.00357","title":"Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models","created":"2024-11-30","cited_by_count":4,"area":"diffusion"},{"id":"2504.14815","title":"What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale","created":"2025-04-21","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":"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":"2603.17828","title":"TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models","created":"2026-03-18","cited_by_count":4,"area":"diffusion"},{"id":"2412.14432","title":"IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features","created":"2024-12-19","cited_by_count":3,"area":null},{"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":"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":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","cited_by_count":3,"area":"safety"},{"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":"2604.10032","title":"Closed-Form Concept Erasure via Double Projections","created":"2026-04-11","cited_by_count":3,"area":"diffusion"},{"id":"2607.23492","title":"To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion","created":"2026-07-26","cited_by_count":3,"area":"diffusion"},{"id":"2408.05794","title":"HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2502.17537","title":"Rethinking the Vulnerability of Concept Erasure and a New Method","created":"2025-02-24","cited_by_count":2,"area":"diffusion"},{"id":"2503.00020","title":"A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.05838","title":"Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"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":"2507.21985","title":"ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models","created":"2025-07-29","cited_by_count":2,"area":"safety"},{"id":"2510.03263","title":"Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models","created":"2025-09-26","cited_by_count":2,"area":"safety"}],"next_cursor":"100"}