{"total":539,"rows":[{"id":"2308.14761","title":"Unified Concept Editing in Diffusion Models","created":"2023-08-25","cited_by_count":388,"area":"diffusion"},{"id":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386,"area":"diffusion"},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372,"area":null},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317,"area":"diffusion"},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307,"area":"diffusion"},{"id":"2303.17591","title":"Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models","created":"2023-03-30","cited_by_count":301,"area":"diffusion"},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"area":"safety"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"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":"2304.04934","title":"Model Sparsity Can Simplify Machine Unlearning","created":"2023-04-11","cited_by_count":214,"area":"safety"},{"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":"2305.10120","title":"Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models","created":"2023-05-17","cited_by_count":177,"area":null},{"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":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160,"area":null},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2311.12092","title":"Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models","created":"2023-11-20","cited_by_count":153,"area":"diffusion"},{"id":"2311.16711","title":"LEDITS++: Limitless Image Editing using Text-to-Image Models","created":"2023-11-28","cited_by_count":148,"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":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110,"area":"safety"},{"id":"2401.04700","title":"Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue","created":"2024-01-09","cited_by_count":103,"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":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"area":"diffusion"},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77,"area":"mechinterp"},{"id":"2309.15664","title":"Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing","created":"2023-09-27","cited_by_count":76,"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":"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":"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":"2311.12832","title":"Toward effective protection against diffusion based mimicry through score distillation","created":"2023-10-02","cited_by_count":65,"area":"diffusion"},{"id":"2306.00926","title":"Inserting Anybody in Diffusion Models via Celeb Basis","created":"2023-06-01","cited_by_count":63,"area":"diffusion"},{"id":"2402.05375","title":"Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models","created":"2024-02-08","cited_by_count":63,"area":"diffusion"},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62,"area":"safety"},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62,"area":null},{"id":"2403.14599","title":"MyVLM: Personalizing VLMs for User-Specific Queries","created":"2024-03-21","cited_by_count":58,"area":"mllm"},{"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":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2405.19237","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","created":"2024-05-29","cited_by_count":55,"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":"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":"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":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","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":"2310.08475","title":"Can We Edit Multimodal Large Language Models?","created":"2023-10-12","cited_by_count":44,"area":"mllm"},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"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":"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":"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":"2312.00084","title":"Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?","created":"2023-11-30","cited_by_count":38,"area":"diffusion"},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2306.01902","title":"Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation","created":"2023-06-02","cited_by_count":37,"area":"diffusion"},{"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":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"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":"2404.00995","title":"PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation","created":"2024-04-01","cited_by_count":35,"area":null},{"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":"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":"2411.07132","title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","created":"2024-11-11","cited_by_count":35,"area":"inference"},{"id":"2401.04136","title":"The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline","created":"2024-01-07","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":"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":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2308.09991","title":"AltDiffusion: A Multilingual Text-to-Image Diffusion Model","created":"2023-08-19","cited_by_count":30,"area":"diffusion"},{"id":"2306.01872","title":"Probabilistic Adaptation of Text-to-Video Models","created":"2023-06-02","cited_by_count":29,"area":"wm"},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2405.07288","title":"Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning","created":"2024-05-12","cited_by_count":29,"area":"diffusion"},{"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":"2405.01008","title":"On Mechanistic Knowledge Localization in Text-to-Image Generative Models","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2405.16821","title":"Perturbation-Restrained Sequential Model Editing","created":"2024-05-27","cited_by_count":28,"area":null},{"id":"2410.14398","title":"Dynamic Negative Guidance of Diffusion Models","created":"2024-10-18","cited_by_count":28,"area":"diffusion"},{"id":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28,"area":"safety"},{"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":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2403.06381","title":"Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models","created":"2024-03-11","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":"2505.12677","title":"CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models","created":"2025-05-19","cited_by_count":27,"area":"diffusion"},{"id":"2307.01827","title":"Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses","created":"2023-07-04","cited_by_count":26,"area":null},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2412.07658","title":"TraSCE: Trajectory Steering for Concept Erasure","created":"2024-12-10","cited_by_count":26,"area":"diffusion"},{"id":"2312.03027","title":"Stable Diffusion Exposed: Gender Bias from Prompt to Image","created":"2023-12-05","cited_by_count":25,"area":"diffusion"},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2503.19783","title":"Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models","created":"2025-03-25","cited_by_count":25,"area":"diffusion"},{"id":"2403.18920","title":"CPR: Retrieval Augmented Generation for Copyright Protection","created":"2024-03-27","cited_by_count":24,"area":"rag"},{"id":"2406.04551","title":"Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance","created":"2024-06-06","cited_by_count":24,"area":null},{"id":"2310.05873","title":"Implicit Concept Removal of Diffusion Models","created":"2023-10-09","cited_by_count":23,"area":"diffusion"},{"id":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23,"area":"safety"},{"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"}],"next_cursor":"100"}