{"total":85,"rows":[{"id":"2501.09004","title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","created":"2025-01-15","cited_by_count":132,"area":"safety"},{"id":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83,"area":"safety"},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62,"area":"safety"},{"id":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52,"area":"safety"},{"id":"2406.05113","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","created":"2024-06-07","cited_by_count":52,"area":"safety"},{"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":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"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":"2408.10848","title":"Perception-guided Jailbreak against Text-to-Image Models","created":"2024-08-20","cited_by_count":40,"area":"safety"},{"id":"2412.06878","title":"SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations","created":"2024-12-09","cited_by_count":38,"area":"safety"},{"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":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"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":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23,"area":"safety"},{"id":"2403.12075","title":"Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation","created":"2024-02-14","cited_by_count":20,"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":"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":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2409.19734","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","created":"2024-09-29","cited_by_count":11,"area":"safety"},{"id":"2504.11106","title":"Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models","created":"2025-04-15","cited_by_count":9,"area":"safety"},{"id":"2506.02761","title":"Rethinking Machine Unlearning in Image Generation Models","created":"2025-06-03","cited_by_count":9,"area":"safety"},{"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":"2305.11351","title":"Data Redaction from Conditional Generative Models","created":"2023-05-18","cited_by_count":8,"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":"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":"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":"2504.15827","title":"DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers","created":"2025-04-22","cited_by_count":6,"area":"safety"},{"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":"2502.16423","title":"Unified Prompt Attack Against Text-to-Image Generation Models","created":"2025-02-23","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":"2504.20376","title":"When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems","created":"2025-04-29","cited_by_count":5,"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":"2505.21347","title":"OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models","created":"2025-05-27","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":"2510.12981","title":"Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check","created":"2025-10-14","cited_by_count":5,"area":"safety"},{"id":"2510.22124","title":"Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery","created":"2025-10-25","cited_by_count":5,"area":"safety"},{"id":"2604.01888","title":"Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters","created":"2026-04-02","cited_by_count":5,"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":"2510.23960","title":"SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability","created":"2025-10-28","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":"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":"2412.08156","title":"Antelope: Potent and Concealed Jailbreak Attack Strategy","created":"2024-12-11","cited_by_count":3,"area":"safety"},{"id":"2506.18325","title":"NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation","created":"2025-06-23","cited_by_count":3,"area":"safety"},{"id":"2507.22499","title":"LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning","created":"2025-07-30","cited_by_count":3,"area":"safety"},{"id":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","cited_by_count":3,"area":"safety"},{"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":"2507.21985","title":"ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models","created":"2025-07-29","cited_by_count":2,"area":"safety"},{"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":"2510.03263","title":"Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models","created":"2025-09-26","cited_by_count":2,"area":"safety"},{"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":"2607.24897","title":"TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models","created":"2026-07-27","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":"2504.01218","title":"Prompting Forgetting: Unlearning in GANs via Textual Guidance","created":"2025-04-01","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":"2603.22870","title":"Designing to Forget: Deep Semi-parametric Models for Unlearning","created":"2026-03-24","cited_by_count":1,"area":"safety"},{"id":"2410.04447","title":"Attention Shift: Steering AI Away from Unsafe Content","created":"2024-10-06","cited_by_count":0,"area":"safety"},{"id":"2507.17922","title":"From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models","created":"2025-07-23","cited_by_count":0,"area":"safety"},{"id":"2510.19226","title":"Controllable Machine Unlearning via Gradient Pivoting","created":"2025-10-22","cited_by_count":0,"area":"safety"},{"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":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2602.19215","title":"Understanding Empirical Unlearning with Combinatorial Interpretability","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2603.15679","title":"IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis","created":"2026-03-14","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":"2604.05853","title":"Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2604.09391","title":"Efficient Unlearning through Maximizing Relearning Convergence Delay","created":"2026-04-10","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":"2605.15737","title":"BARRIER: Bounded Activation Regions for Robust Information Erasure","created":"2026-05-15","cited_by_count":0,"area":"safety"},{"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":"2606.17122","title":"TrustErase: Auditable Instant Machine Unlearning with Passport-Embedded Representations","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2606.24081","title":"PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.14194","title":"Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Models","created":"2026-07-15","cited_by_count":0,"area":"safety"},{"id":"2607.17779","title":"Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models","created":"2026-07-20","cited_by_count":0,"area":"safety"},{"id":"2607.24101","title":"LU-500: A Logo Benchmark for Concept Unlearning","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2608.13478","title":"MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning","created":"2026-08-13","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":"2608.29589","title":"Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines","created":"2026-08-30","cited_by_count":0,"area":"safety"},{"id":"2609.05117","title":"TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors","created":"2026-09-04","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":"2609.31032","title":"TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks","created":"2026-09-25","cited_by_count":0,"area":"safety"},{"id":"2609.34920","title":"RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models","created":"2026-09-28","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"},{"id":"2610.06503","title":"Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations","created":"2026-10-05","cited_by_count":0,"area":"safety"}],"next_cursor":null}