{"total":72,"rows":[{"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":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"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":"2408.10848","title":"Perception-guided Jailbreak against Text-to-Image Models","created":"2024-08-20","cited_by_count":40,"area":"safety"},{"id":"2410.12777","title":"Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts","created":"2024-10-16","cited_by_count":40,"area":"diffusion"},{"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":"2502.13175","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","created":"2025-02-18","cited_by_count":34,"area":null},{"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":"2503.15092","title":"Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings","created":"2025-03-19","cited_by_count":27,"area":null},{"id":"2501.13772","title":"Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models","created":"2025-01-23","cited_by_count":23,"area":"safety"},{"id":"2408.11071","title":"DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization","created":"2024-08-18","cited_by_count":22,"area":"diffusion"},{"id":"2410.05664","title":"Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning","created":"2024-10-08","cited_by_count":21,"area":"diffusion"},{"id":"2412.05892","title":"PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization","created":"2024-12-08","cited_by_count":17,"area":"mllm"},{"id":"2410.08074","title":"Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models","created":"2024-10-10","cited_by_count":15,"area":"diffusion"},{"id":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2410.02710","title":"SteerDiff: Steering towards Safe Text-to-Image Diffusion Models","created":"2024-10-03","cited_by_count":10,"area":"diffusion"},{"id":"2410.21471","title":"AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models","created":"2024-10-28","cited_by_count":10,"area":"diffusion"},{"id":"2507.07139","title":"Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning","created":"2025-07-09","cited_by_count":10,"area":"diffusion"},{"id":"2509.24368","title":"Watermarking Diffusion Language Models","created":"2025-09-29","cited_by_count":10,"area":"diffusion"},{"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":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","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":"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":"2412.05538","title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2507.21820","title":"Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is","created":"2025-07-29","cited_by_count":7,"area":"safety"},{"id":"2408.09798","title":"Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting","created":"2024-08-19","cited_by_count":5,"area":"safety"},{"id":"2510.15476","title":"SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses","created":"2025-10-17","cited_by_count":5,"area":"safety"},{"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":"2604.01888","title":"Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters","created":"2026-04-02","cited_by_count":5,"area":"safety"},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"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":"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":"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":"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":"2510.24820","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":"2511.19558","title":"SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation","created":"2025-11-24","cited_by_count":2,"area":"diffusion"},{"id":"2601.07141","title":"MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models","created":"2026-01-12","cited_by_count":2,"area":"safety"},{"id":"2603.27332","title":"Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models","created":"2026-03-28","cited_by_count":2,"area":null},{"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":"2412.13705","title":"Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2507.07947","title":"Reconstructing Template-Memorized Images from Natural Prompts","created":"2025-07-10","cited_by_count":1,"area":"diffusion"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2509.20230","title":"Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization","created":"2025-09-24","cited_by_count":1,"area":"safety"},{"id":"2601.05150","title":"$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models","created":"2026-01-08","cited_by_count":1,"area":"safety"},{"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":"2603.11664","title":"BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder","created":"2026-03-12","cited_by_count":1,"area":"mllm"},{"id":"2604.11309","title":"The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems","created":"2026-04-13","cited_by_count":1,"area":"safety"},{"id":"2604.25119","title":"Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2412.01725","title":"Attacks on multimodal models","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2506.18248","title":"Improving Black-Box Generative Attacks via Generator Semantic Consistency","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2511.21180","title":"CAHS-Attack: CLIP-Aware Heuristic Search Attack Method for Stable Diffusion","created":"2025-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2512.08724","title":"Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search","created":"2025-12-09","cited_by_count":0,"area":"diffusion"},{"id":"2512.11194","title":"Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Training","created":"2025-12-12","cited_by_count":0,"area":"diffusion"},{"id":"2602.00350","title":"ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models","created":"2026-01-30","cited_by_count":0,"area":"diffusion"},{"id":"2603.10689","title":"Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?","created":"2026-03-11","cited_by_count":0,"area":null},{"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":"2605.00699","title":"STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.20654","title":"REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"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":"2607.05407","title":"Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.21869","title":"GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration","created":"2026-08-22","cited_by_count":0,"area":"diffusion"},{"id":"2608.24068","title":"Representation Learning in Diffusion and Flow-based Model: An Application Aspect","created":"2026-08-25","cited_by_count":0,"area":"diffusion"},{"id":"2608.26535","title":"Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation","created":"2026-08-27","cited_by_count":0,"area":null},{"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":"2609.33445","title":"Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"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":"2610.05908","title":"Safe Image Generation via Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}