{"total":133,"rows":[{"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":"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":"2503.07392","title":"SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models","created":"2025-03-10","cited_by_count":36,"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":"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":"2502.08011","title":"Training-Free Safe Denoisers for Safe Use of Diffusion Models","created":"2025-02-11","cited_by_count":21,"area":"diffusion"},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18,"area":"safety"},{"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":"2503.07050","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation","created":"2025-03-10","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":"2505.17550","title":"T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models","created":"2025-05-23","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":"2508.15314","title":"VideoEraser: Concept Erasure in Text-to-Video Diffusion Models","created":"2025-08-21","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":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2507.13386","title":"Minimalist Concept Erasure in Generative Models","created":"2025-07-16","cited_by_count":13,"area":null},{"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":"2505.01456","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","created":"2025-05-01","cited_by_count":11,"area":"mllm"},{"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":"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":"2511.00804","title":"EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment","created":"2025-11-02","cited_by_count":9,"area":"alignment"},{"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":"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":"2510.22851","title":"Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models","created":"2025-10-26","cited_by_count":8,"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":"2502.15082","title":"UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning","created":"2025-02-20","cited_by_count":7,"area":"safety"},{"id":"2505.18832","title":"Localizing Knowledge in Diffusion Transformers","created":"2025-05-24","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":"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":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7,"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":"2603.13300","title":"Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation","created":"2026-03-02","cited_by_count":6,"area":null},{"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":"2512.23546","title":"PurifyGen: A Risk-Discrimination and Semantic-Purification Model for Safe Text-to-Image Generation","created":"2025-12-29","cited_by_count":5,"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":"2603.25994","title":"Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models","created":"2026-03-27","cited_by_count":4,"area":"diffusion"},{"id":"2606.24192","title":"Co-occurring Associated REtained concepts in Diffusion Unlearning","created":"2026-06-23","cited_by_count":4,"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":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","cited_by_count":3,"area":"safety"},{"id":"2602.19631","title":"Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection","created":"2026-02-23","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":"2606.04775","title":"Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control","created":"2026-06-03","cited_by_count":3,"area":"mechinterp"},{"id":"2501.03271","title":"DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization","created":"2025-01-05","cited_by_count":2,"area":"alignment"},{"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":"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":"2509.16986","title":"VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2509.21167","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","created":"2025-09-25","cited_by_count":2,"area":"diffusion"},{"id":"2509.21360","title":"Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models","created":"2025-09-21","cited_by_count":2,"area":"safety"},{"id":"2510.17917","title":"Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning","created":"2025-10-20","cited_by_count":2,"area":"diffusion"},{"id":"2510.24820","title":"SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing","created":"2025-10-28","cited_by_count":2,"area":"safety"},{"id":"2511.11693","title":"Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image Generation","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2602.07919","title":"Selective Fine-Tuning for Targeted and Robust Concept Unlearning","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2604.01826","title":"SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers","created":"2026-04-02","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":"2605.28902","title":"Orthogonal Concept Erasure for Diffusion Models","created":"2026-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2411.16769","title":"Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting","created":"2024-11-25","cited_by_count":1,"area":"safety"},{"id":"2506.08991","title":"Do Concept Replacement Techniques Really Erase Unacceptable Concepts?","created":"2025-06-10","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":"2510.03089","title":"Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbations","created":"2025-10-03","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":"2511.04834","title":"Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models","created":"2025-11-06","cited_by_count":1,"area":"diffusion"},{"id":"2601.20791","title":"FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models","created":"2026-01-28","cited_by_count":1,"area":"diffusion"},{"id":"2603.00978","title":"EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization","created":"2026-03-01","cited_by_count":1,"area":"diffusion"},{"id":"2603.08271","title":"Prototype-Guided Concept Erasure in Diffusion Models","created":"2026-03-09","cited_by_count":1,"area":"diffusion"},{"id":"2603.10445","title":"Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models","created":"2026-03-11","cited_by_count":1,"area":"diffusion"},{"id":"2603.21547","title":"PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models","created":"2026-03-23","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":"2604.04575","title":"Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models","created":"2026-04-06","cited_by_count":1,"area":"diffusion"},{"id":"2604.09405","title":"EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure","created":"2026-04-10","cited_by_count":1,"area":"diffusion"},{"id":"2604.16483","title":"DSS: Dynamic Semantic Steering for Robust Concept Erasure in Diffusion Models","created":"2026-04-13","cited_by_count":1,"area":"diffusion"},{"id":"2605.10180","title":"What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers","created":"2026-05-11","cited_by_count":1,"area":"diffusion"},{"id":"2605.10198","title":"Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models","created":"2026-05-11","cited_by_count":1,"area":"diffusion"},{"id":"2605.25941","title":"Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2606.23267","title":"Safe Few-Step Generation via Velocity Editing","created":"2026-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2606.25592","title":"VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.27147","title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2606.28643","title":"Obliviate: Erasing Concepts from Autoregressive Image Generation Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.12829","title":"Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers","created":"2026-08-13","cited_by_count":1,"area":"diffusion"},{"id":"2610.01969","title":"RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models","created":"2026-10-01","cited_by_count":1,"area":"diffusion"},{"id":"2610.03980","title":"FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning","created":"2026-10-02","cited_by_count":1,"area":"diffusion"},{"id":"2610.05601","title":"Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models","created":"2026-10-04","cited_by_count":1,"area":"diffusion"},{"id":"2411.17077","title":"ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts","created":"2024-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2502.03512","title":"YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment","created":"2025-02-05","cited_by_count":0,"area":"alignment"},{"id":"2505.08817","title":"Towards SFW sampling for diffusion models via external conditioning","created":"2025-05-12","cited_by_count":0,"area":"diffusion"},{"id":"2508.04472","title":"Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2510.26052","title":"Dynamic VLM-Guided Negative Prompting for Diffusion Models","created":"2025-10-30","cited_by_count":0,"area":"mllm"},{"id":"2511.11014","title":"SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation","created":"2025-11-14","cited_by_count":0,"area":"safety"},{"id":"2512.10720","title":"Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"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":"2602.05339","title":"Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation","created":"2026-02-05","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":"2604.02265","title":"Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.06063","title":"EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.25765","title":"Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models","created":"2026-05-25","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":"2606.06356","title":"Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Model","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":"100"}