English
Related papers

Related papers: No Safe Dose: How Training Data Drives Unsafe Imag…

200 papers

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Samuele Poppi , Tobia Poppi , Federico Cocchi , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful images, even when…

Cryptography and Security · Computer Science 2025-03-03 Yuepeng Hu , Zhengyuan Jiang , Neil Zhenqiang Gong

State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Yiting Qu , Xinyue Shen , Xinlei He , Michael Backes , Savvas Zannettou , Yang Zhang

There is growing concern over the safety of powerful diffusion models (DMs), as they are often misused to produce inappropriate, not-safe-for-work (NSFW) content or generate copyrighted material or data of individuals who wish to be…

Artificial Intelligence · Computer Science 2026-02-24 Mingyu Kim , Dongjun Kim , Amman Yusuf , Stefano Ermon , Mijung Park

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

Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Lijie Fan , Kaifeng Chen , Dilip Krishnan , Dina Katabi , Phillip Isola , Yonglong Tian

Recent text-to-image diffusion models have shown surprising performance in generating high-quality images. However, concerns have arisen regarding the unauthorized data usage during the training or fine-tuning process. One example is when a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Zhenting Wang , Chen Chen , Lingjuan Lyu , Dimitris N. Metaxas , Shiqing Ma

Text-to-image models have recently made significant advances in generating realistic and semantically coherent images, driven by advanced diffusion models and large-scale web-crawled datasets. However, these datasets often contain…

Machine Learning · Computer Science 2025-10-29 Byeonghu Na , Mina Kang , Jiseok Kwak , Minsang Park , Jiwoo Shin , SeJoon Jun , Gayoung Lee , Jin-Hwa Kim , Il-Chul Moon

High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated by these generative…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Yuechen Xie , Jie Song , Huiqiong Wang , Mingli Song

Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Jaehong Yoon , Shoubin Yu , Vaidehi Patil , Huaxiu Yao , Mohit Bansal

Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Manuel Brack , Sudeep Katakol , Felix Friedrich , Patrick Schramowski , Hareesh Ravi , Kristian Kersting , Ajinkya Kale

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders…

Machine Learning · Computer Science 2023-08-10 Lukas Struppek , Dominik Hintersdorf , Kristian Kersting

With the advent of text-to-image models and concerns about their misuse, developers are increasingly relying on image safety classifiers to moderate their generated unsafe images. Yet, the performance of current image safety classifiers…

Cryptography and Security · Computer Science 2025-09-12 Yiting Qu , Xinyue Shen , Yixin Wu , Michael Backes , Savvas Zannettou , Yang Zhang

In recent years, text-to-image (T2I) generation models have made significant progress in generating high-quality images that align with text descriptions. However, these models also face the risk of unsafe generation, potentially producing…

Cryptography and Security · Computer Science 2025-04-16 Huming Qiu , Guanxu Chen , Mi Zhang , Xiaohan Zhang , Xiaoyu You , Min Yang

The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of data annotations, typically requiring the engagement of…

Computer Vision and Pattern Recognition · Computer Science 2024-06-26 Joshua Niemeijer , Jan Ehrhardt , Hristina Uzunova , Heinz Handels

Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic data. However, every synthetic image ultimately originates from…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Scott Geng , Cheng-Yu Hsieh , Vivek Ramanujan , Matthew Wallingford , Chun-Liang Li , Pang Wei Koh , Ranjay Krishna

Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make incremental updates to existing models. These updates often…

Machine Learning · Computer Science 2025-09-29 Vinith M. Suriyakumar , Rohan Alur , Ayush Sekhari , Manish Raghavan , Ashia C. Wilson

Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful capabilities. In this paper, we investigate the proactive…

Cryptography and Security · Computer Science 2025-02-06 Yixin Wu , Ning Yu , Michael Backes , Yun Shen , Yang Zhang

The current state-of-the-art Diffusion model has demonstrated excellent results in generating images. However, the images are monotonous and are mostly the result of the distribution of images of people in the training set, making it…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Tianyu Chen

Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Xinfeng Li , Yuchen Yang , Jiangyi Deng , Chen Yan , Yanjiao Chen , Xiaoyu Ji , Wenyuan Xu
‹ Prev 1 2 3 10 Next ›