{"total":35,"rows":[{"id":"2502.05374","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","created":"2025-02-07","cited_by_count":79,"area":"safety"},{"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":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2503.06339","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","created":"2025-03-08","cited_by_count":19,"area":"safety"},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2411.15537","title":"MUNBa: Machine Unlearning via Nash Bargaining","created":"2024-11-23","cited_by_count":17,"area":"safety"},{"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":"2506.14003","title":"Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs","created":"2025-06-16","cited_by_count":11,"area":"safety"},{"id":"2506.02761","title":"Rethinking Machine Unlearning in Image Generation Models","created":"2025-06-03","cited_by_count":9,"area":"safety"},{"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":"2412.16780","title":"Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification","created":"2024-12-21","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":"2406.16810","title":"How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective","created":"2024-06-24","cited_by_count":5,"area":"safety"},{"id":"2503.01839","title":"Jailbreaking Safeguarded Text-to-Image Models via Large Language Models","created":"2025-03-03","cited_by_count":5,"area":"safety"},{"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":"2506.01318","title":"Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack","created":"2025-06-02","cited_by_count":4,"area":"safety"},{"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":"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":"2601.08623","title":"SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2503.00917","title":"AMUN: Adversarial Machine UNlearning","created":"2025-03-02","cited_by_count":2,"area":"safety"},{"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"},{"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":"2504.14798","title":"RUB: Evaluating Residual Knowledge in Unlearned Models","created":"2025-04-21","cited_by_count":1,"area":"safety"},{"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":"2506.11253","title":"Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models","created":"2025-06-12","cited_by_count":0,"area":"safety"},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2603.16576","title":"REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.15967","title":"When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models","created":"2026-04-17","cited_by_count":0,"area":"safety"},{"id":"2605.11592","title":"SoK: Unlearnability and Unlearning for Model Dememorization","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.15737","title":"BARRIER: Bounded Activation Regions for Robust Information Erasure","created":"2026-05-15","cited_by_count":0,"area":"safety"},{"id":"2606.29880","title":"IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"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":"2609.25166","title":"Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning","created":"2026-09-21","cited_by_count":0,"area":"safety"},{"id":"2609.39605","title":"FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}