{"total":66,"rows":[{"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":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45,"area":null},{"id":"2412.05934","title":"Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models","created":"2024-12-08","cited_by_count":33,"area":"safety"},{"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":"2507.03034","title":"Rethinking Data Protection in the (Generative) Artificial Intelligence Era","created":"2025-07-03","cited_by_count":18,"area":null},{"id":"2501.03544","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","created":"2025-01-07","cited_by_count":17,"area":"safety"},{"id":"2510.11108","title":"A Vision for Access Control in LLM-based Agent Systems","created":"2025-10-13","cited_by_count":14,"area":"agents"},{"id":"2408.00001","title":"Replication in Visual Diffusion Models: A Survey and Outlook","created":"2024-07-07","cited_by_count":11,"area":"diffusion"},{"id":"2510.00181","title":"CHAI: Command Hijacking against embodied AI","created":"2025-09-30","cited_by_count":11,"area":null},{"id":"2407.12581","title":"Towards Understanding Unsafe Video Generation","created":"2024-07-17","cited_by_count":10,"area":null},{"id":"2411.17957","title":"DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing","created":"2024-11-27","cited_by_count":10,"area":null},{"id":"2504.21072","title":"Erased but Not Forgotten: How Backdoors Compromise Concept Erasure","created":"2025-04-29","cited_by_count":9,"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":"2508.03696","title":"PLA: Prompt Learning Attack against Text-to-Image Generative Models","created":"2025-07-14","cited_by_count":9,"area":"safety"},{"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":"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":"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":"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":"2502.20623","title":"SafeText: Safe Text-to-image Models via Aligning the Text Encoder","created":"2025-02-28","cited_by_count":7,"area":null},{"id":"2602.06258","title":"GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt","created":"2026-02-05","cited_by_count":7,"area":"alignment"},{"id":"2503.12874","title":"Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models","created":"2025-03-17","cited_by_count":6,"area":"mllm"},{"id":"2509.21433","title":"DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation","created":"2025-09-25","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":"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":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","cited_by_count":4,"area":"safety"},{"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":"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":"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":"2603.03163","title":"Conditioned Activation Transport for T2I Safety Steering","created":"2026-03-03","cited_by_count":3,"area":"mechinterp"},{"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":"2504.14554","title":"REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models","created":"2025-04-20","cited_by_count":2,"area":"diffusion"},{"id":"2508.01272","title":"PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2508.21099","title":"Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2510.21120","title":"SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2603.24079","title":"When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm","created":"2026-03-25","cited_by_count":2,"area":"mllm"},{"id":"2605.19739","title":"FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models","created":"2026-05-19","cited_by_count":2,"area":"diffusion"},{"id":"2506.08991","title":"Do Concept Replacement Techniques Really Erase Unacceptable Concepts?","created":"2025-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2507.07056","title":"LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing","created":"2025-07-05","cited_by_count":1,"area":"safety"},{"id":"2510.16581","title":"Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2512.03564","title":"Towards Irreversible Machine Unlearning for Diffusion Models","created":"2025-12-03","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":"2604.06285","title":"Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization","created":"2026-04-07","cited_by_count":1,"area":"mllm"},{"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":"2505.08817","title":"Towards SFW sampling for diffusion models via external conditioning","created":"2025-05-12","cited_by_count":0,"area":"diffusion"},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2512.12501","title":"SafeGen: Embedding Ethical Safeguards in Text-to-Image Generation","created":"2025-12-14","cited_by_count":0,"area":"diffusion"},{"id":"2603.00992","title":"Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information","created":"2026-03-01","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":"2606.14351","title":"ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models","created":"2026-06-12","cited_by_count":0,"area":"safety"},{"id":"2606.15819","title":"SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models","created":"2026-06-14","cited_by_count":0,"area":"alignment"},{"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":"2608.17067","title":"DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization","created":"2026-08-17","cited_by_count":0,"area":"safety"},{"id":"2609.27620","title":"InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation","created":"2026-09-23","cited_by_count":0,"area":"safety"},{"id":"2609.39688","title":"ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.01989","title":"Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference","created":"2026-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2610.05908","title":"Safe Image Generation via Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"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}