{"total":49,"rows":[{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"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":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71,"area":null},{"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":"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":"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":"2309.14122","title":"SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution","created":"2023-09-25","cited_by_count":34,"area":null},{"id":"2401.03315","title":"Malla: Demystifying Real-world Large Language Model Integrated Malicious Services","created":"2024-01-06","cited_by_count":33,"area":null},{"id":"2402.10882","title":"Universal Prompt Optimizer for Safe Text-to-Image Generation","created":"2024-02-16","cited_by_count":28,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2311.18815","title":"IMMA: Immunizing text-to-image Models against Malicious Adaptation","created":"2023-11-30","cited_by_count":18,"area":null},{"id":"2402.01787","title":"Harm Amplification in Text-to-Image Models","created":"2024-02-01","cited_by_count":15,"area":null},{"id":"2402.12100","title":"Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation","created":"2024-02-19","cited_by_count":14,"area":null},{"id":"2406.07353","title":"Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities","created":"2024-06-11","cited_by_count":13,"area":null},{"id":"2507.13386","title":"Minimalist Concept Erasure in Generative Models","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2407.12581","title":"Towards Understanding Unsafe Video Generation","created":"2024-07-17","cited_by_count":10,"area":null},{"id":"2402.15218","title":"BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2412.18123","title":"AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2502.20623","title":"SafeText: Safe Text-to-image Models via Aligning the Text Encoder","created":"2025-02-28","cited_by_count":7,"area":null},{"id":"2312.00057","title":"VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2412.21052","title":"Towards Effective Discrimination Testing for Generative AI","created":"2024-12-30","cited_by_count":5,"area":null},{"id":"2505.04673","title":"REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2404.12104","title":"Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2411.10329","title":"Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2512.17320","title":"EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2306.11393","title":"The Cultivated Practices of Text-to-Image Generation","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2402.07562","title":"Discovering Universal Semantic Triggers for Text-to-Image Synthesis","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2508.01272","title":"PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2509.10359","title":"Immunizing Images from Text to Image Editing via Adversarial Cross-Attention","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2509.16986","title":"VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2403.02118","title":"Position: Towards Implicit Prompt For Text-To-Image Models","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2510.16581","title":"Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries","created":"2025-10-18","cited_by_count":1,"area":null},{"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":"2606.05829","title":"Gender Artifacts from Art History to Text-to-Image Generation","created":"2026-06-04","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":"2607.00948","title":"Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.05210","title":"Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2408.05476","title":"Artworks Reimagined: Exploring Human-AI Co-Creation through Body Prompting","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2409.06107","title":"Doppelg\\\"anger's Watch: A Split Objective Approach to Large Language Models","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2503.18273","title":"Decoding Islamophobic Discourse: Using LLMs to Identify Tropes and Semi-Coded Hate Speech","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2603.20201","title":"FIGURA: A Modular Prompt Engineering Method for Artistic Figure Photography in Safety-Filtered Text-to-Image Models","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.00874","title":"Latent Space Probing for Adult Content Detection in Video Generative Models","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.09606","title":"On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.15398","title":"3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.28137","title":"No Safe Dose: How Training Data Drives Unsafe Image Generation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.25548","title":"Concept Removal for Frontier Image Generative Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27234","title":"From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}