{"total":75,"rows":[{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336,"area":null},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"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":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66,"area":null},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63,"area":null},{"id":"2211.14946","title":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","created":"2022-11-27","cited_by_count":57,"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":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"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":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"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":"2404.03631","title":"Robust Concept Erasure Using Task Vectors","created":"2024-04-04","cited_by_count":27,"area":null},{"id":"2501.00192","title":"MLLM-as-a-Judge for Image Safety without Human Labeling","created":"2024-12-31","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":"2306.06135","title":"Safety and Fairness for Content Moderation in Generative Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2402.01787","title":"Harm Amplification in Text-to-Image Models","created":"2024-02-01","cited_by_count":15,"area":null},{"id":"2410.04772","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2410.09140","title":"RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining","created":"2024-10-11","cited_by_count":15,"area":null},{"id":"2403.02580","title":"What do we learn from inverting CLIP models?","created":"2024-03-05","cited_by_count":13,"area":null},{"id":"2405.11336","title":"UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers","created":"2024-05-18","cited_by_count":12,"area":null},{"id":"2501.01125","title":"DuMo: Dual Encoder Modulation Network for Precise Concept Erasure","created":"2025-01-02","cited_by_count":11,"area":null},{"id":"2307.10223","title":"Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms","created":"2023-07-15","cited_by_count":10,"area":null},{"id":"2407.12581","title":"Towards Understanding Unsafe Video Generation","created":"2024-07-17","cited_by_count":10,"area":null},{"id":"2505.19398","title":"Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2506.08071","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","cited_by_count":7,"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":"2406.14599","title":"Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"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":"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":"2503.09805","title":"Un-Straightening Generative AI: How Queer Artists Surface and Challenge the Normativity of Generative AI Models","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2311.15936","title":"Towards Responsible Governance of Biological Design Tools","created":"2023-11-27","cited_by_count":5,"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":"2503.18324","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2410.10852","title":"SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance","created":"2024-10-06","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":"2501.12374","title":"Expertise elevates AI usage: experimental evidence comparing laypeople and professional artists","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2502.17710","title":"Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures","created":"2025-02-24","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":"2402.07562","title":"Discovering Universal Semantic Triggers for Text-to-Image Synthesis","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2404.05580","title":"Responsible Visual Editing","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2408.05794","title":"HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2501.18669","title":"The Pitfalls of \"Security by Obscurity\" And What They Mean for Transparent AI","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2508.21099","title":"Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification","created":"2025-08-28","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":"2411.13982","title":"Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2502.16701","title":"Beyond Release: Access Considerations for Generative AI Systems","created":"2025-02-23","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":"2606.27147","title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","created":"2026-06-25","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":"2403.08017","title":"Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2409.10297","title":"On Synthetic Texture Datasets: Challenges, Creation, and Curation","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2412.12212","title":"Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2508.04472","title":"Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2510.21842","title":"Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?","created":"2025-10-22","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":"2604.02265","title":"Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.06063","title":"EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching","created":"2026-04-04","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":"2605.29390","title":"Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.06356","title":"Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Model","created":"2026-06-04","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":"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":"2607.14945","title":"Introspective Attention Modulation for Safe Text-to-Image Generation","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.31154","title":"HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.02300","title":"Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}