English
Related papers

Related papers: Prompting4Debugging: Red-Teaming Text-to-Image Dif…

200 papers

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Xuehai He , Weixi Feng , Tsu-Jui Fu , Varun Jampani , Arjun Akula , Pradyumna Narayana , Sugato Basu , William Yang Wang , Xin Eric Wang

Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content. Among various editing methods, editing within the prompt space gains more…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Aosong Feng , Weikang Qiu , Jinbin Bai , Xiao Zhang , Zhen Dong , Kaicheng Zhou , Rex Ying , Leandros Tassiulas

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of attack prompts…

Computation and Language · Computer Science 2025-03-03 Seanie Lee , Minsu Kim , Lynn Cherif , David Dobre , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi , Gauthier Gidel , Yoshua Bengio , Nikolay Malkin , Moksh Jain

Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yixin Liu , Ruoxi Chen , Xun Chen , Lichao Sun

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

Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality depends critically on well-crafted prompts that specify both…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mingzhe Li , Renhao Zhang , Zhiyang Wen , Siqi Pan , Bruno Castro da Silva , Juan Zhai , Shiqing Ma

Text-to-image diffusion models have achieved remarkable success in generating high-quality contents from text prompts. However, their reliance on publicly available data and the growing trend of data sharing for fine-tuning make these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Sangwon Jang , June Suk Choi , Jaehyeong Jo , Kimin Lee , Sung Ju Hwang

Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, there is a dearth of…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Ruipeng Ma , Jinhao Duan , Fei Kong , Xiaoshuang Shi , Kaidi Xu

Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing…

Machine Learning · Computer Science 2026-03-18 Manos Plitsis , Giorgos Bouritsas , Vassilis Katsouros , Yannis Panagakis

Recent advancements in Text-to-Image (T2I) diffusion models have demonstrated impressive success in generating high-quality images with zero-shot generalization capabilities. Yet, current models struggle to closely adhere to prompt…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Hyun Kang , Dohae Lee , Myungjin Shin , In-Kwon Lee

Text-to-Image (T2I) models, represented by DALL$\cdot$E and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the carefully engineered prompts, which have become valuable…

Cryptography and Security · Computer Science 2026-01-22 Shiqian Zhao , Chong Wang , Yiming Li , Yihao Huang , Wenjie Qu , Siew-Kei Lam , Yi Xie , Kangjie Chen , Jie Zhang , Tianwei Zhang

Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Hadas Orgad , Bahjat Kawar , Yonatan Belinkov

The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Training (CLIP). However, text prompts have limitations when it…

Computer Vision and Pattern Recognition · Computer Science 2024-02-16 Yuxuan Ding , Chunna Tian , Haoxuan Ding , Lingqiao Liu

Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while preserving behavior on benign prompts. We study this tension relative to the frozen generator,…

Artificial Intelligence · Computer Science 2026-05-14 Minhyuk Lee , Hyekyung Yoon , Myungjoo Kang

Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process. Unfortunately, the high fidelity also comes at a high computational cost due the inherently…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Qinchan Li , Kenneth Chen , Changyue Su , Wittawat Jitkrittum , Qi Sun , Patsorn Sangkloy

Recent advances in diffusion models have notably enhanced text-to-image (T2I) generation quality, but they also raise the risk of generating unsafe content. Traditional safety methods like text blacklisting or harmful content classification…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Zongsheng Cao , Yangfan He , Anran Liu , Jun Xie , Feng Chen , Zepeng Wang

Text-to-image generation has recently emerged as a viable alternative to text-to-image retrieval, driven by the visually impressive results of generative diffusion models. Although query performance prediction is an active research topic in…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Eduard Poesina , Adriana Valentina Costache , Adrian-Gabriel Chifu , Josiane Mothe , Radu Tudor Ionescu

Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Contrary to expectations, our investigations reveal that the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Xiaosen Wang , Zhijin Ge , Shaokang Wang

Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Mingyang Yi , Aoxue Li , Yi Xin , Zhenguo Li

Diffusion models equipped with language models demonstrate excellent controllability in image generation tasks, allowing image processing to adhere to human instructions. However, the lack of diverse instruction-following data hampers the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Yongsheng Yu , Ziyun Zeng , Hang Hua , Jianlong Fu , Jiebo Luo