English
Related papers

Related papers: Personalized Safety Alignment for Text-to-Image Di…

200 papers

From biotechnology to cyber-risks, most extreme technological risks cannot be reliably estimated from historical statistics. Therefore, engineers resort to predictive methods, such as fault/event trees in the framework of probabilistic…

Physics and Society · Physics 2014-08-26 D. Sornette , T. Maillart , W. Kroeger

Graph-based learning excels at capturing interaction patterns in diverse domains like recommendation, fraud detection, and particle physics. However, its performance often degrades under distribution shifts, especially those altering…

Machine Learning · Computer Science 2026-05-12 Hans Hao-Hsun Hsu , Shikun Liu , Han Zhao , Pan Li

Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Chao Zhou , Tianyi Wei , Nenghai Yu

Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of…

Cryptography and Security · Computer Science 2024-10-14 Guanlin Li , Kangjie Chen , Shudong Zhang , Jie Zhang , Tianwei Zhang

Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Shufan Li , Harkanwar Singh , Aditya Grover

Advances in generative models have led to significant interest in image synthesis, demonstrating the ability to generate high-quality images for a diverse range of text prompts. Despite this progress, most studies ignore the presence of…

Artificial Intelligence · Computer Science 2024-07-02 Nila Masrourisaadat , Nazanin Sedaghatkish , Fatemeh Sarshartehrani , Edward A. Fox

Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Hao Zou , Runqing Zhang , Xue Zhou , Jianxiao Zou

Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. However, existing UDA methods largely ignore the instantaneous data distribution during model…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Zongxian Li , Qixiang Ye , Chong Zhang , Jingjing Liu , Shijian Lu , Yonghong Tian

Recent advancements in diffusion-based text-to-image (T2I) models have enabled the generation of high-quality and photorealistic images from text. However, they often exhibit societal biases related to gender, race, and socioeconomic…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Jeonghoon Park , Juyoung Lee , Chaeyeon Chung , Jaeseong Lee , Jaegul Choo , Jindong Gu

Generative artificial intelligence (GenAI) has made significant progress in understanding world knowledge and generating content from human languages across various modalities, like text-to-text large language models, text-to-image stable…

Machine Learning · Computer Science 2025-03-27 Zexi Li , Lingzhi Gao , Chao Wu

Large-scale decentralized learning frameworks such as federated learning (FL), require both communication efficiency and strong data security, motivating the study of secure aggregation (SA). While information-theoretic SA is well…

Information Theory · Computer Science 2026-01-28 Xiang Zhang , Zhou Li , Han Yu , Kai Wan , Hua Sun , Mingyue Ji , Giuseppe Caire

Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic…

Computation and Language · Computer Science 2026-05-11 Xiaochen Zheng , Zhiwen Jiang , Melanie Guerard , Klas Hatje , Tatyana Doktorova

Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remains uneven across agencies and community stakeholders. Technical prerequisites create a…

Computation and Language · Computer Science 2026-05-22 Mahdi Azhdari , Eric J. Gonzales

Text-to-image generation has witnessed significant progress with the advent of diffusion models. Despite the ability to generate photorealistic images, current text-to-image diffusion models still often struggle to accurately interpret and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Tsung-Han Wu , Long Lian , Joseph E. Gonzalez , Boyi Li , Trevor Darrell

Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Seoyun Yang , Gihoon Kim , Taesup Kim

We perform a risk assessment of the Public Safety Assessment (PSA), a software used in San Francisco and other jurisdictions to assist judges in deciding whether defendants need to be detained before their trial. With a mixed-methods…

Computers and Society · Computer Science 2020-05-18 Marc Faddoul , Henriette Ruhrmann , Joyce Lee

Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW,…

Computers and Society · Computer Science 2025-08-29 Matthias Schneider , Thilo Hagendorff

Text-to-image models, such as Stable Diffusion (SD), undergo iterative updates to improve image quality and address concerns such as safety. Improvements in image quality are straightforward to assess. However, how model updates resolve…

Cryptography and Security · Computer Science 2024-09-02 Yixin Wu , Yun Shen , Michael Backes , Yang Zhang

We address the problem of interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Ofir Nabati , Guy Tennenholtz , ChihWei Hsu , Moonkyung Ryu , Deepak Ramachandran , Yinlam Chow , Xiang Li , Craig Boutilier

The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma: to prevent misuse, they are forced to damage the model's…

Cryptography and Security · Computer Science 2026-03-18 Lingyun Zhang , Yu Xie , Ping Chen