中文
相关论文

相关论文: SecureT2I: No More Unauthorized Manipulation on AI…

200 篇论文

Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency. However, such fine-tuned models are not robust; they often fail to compose with concepts of pretrained…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Kyungmin Lee , Sangkyung Kwak , Kihyuk Sohn , Jinwoo Shin

The success of recent text-to-image diffusion models is largely due to their capacity to be guided by a complex text prompt, which enables users to precisely describe the desired content. However, these models struggle to effectively…

计算机视觉与模式识别 · 计算机科学 2024-02-09 Senmao Li , Joost van de Weijer , Taihang Hu , Fahad Shahbaz Khan , Qibin Hou , Yaxing Wang , Jian Yang

Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vulnerability to backdoor attacks. Existing attack methods…

密码学与安全 · 计算机科学 2025-08-05 Haoran Dai , Jiawen Wang , Ruo Yang , Manali Sharma , Zhonghao Liao , Yuan Hong , Binghui Wang

Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and harmful content raises…

计算机视觉与模式识别 · 计算机科学 2025-06-09 Changhoon Kim , Yanjun Qi

Recent advances in diffusion models have enabled high-quality generation and manipulation of images guided by texts, as well as concept learning from images. However, naive applications of existing methods to editing tasks that require…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Xudong Liu , Zikun Chen , Ruowei Jiang , Ziyi Wu , Kejia Yin , Han Zhao , Parham Aarabi , Igor Gilitschenski

This paper analyzes the community safety guidelines of five text-to-image (T2I) generation platforms and audits five T2I models, focusing on prompts related to the representation of humans in areas that might lead to societal stigma. While…

计算机与社会 · 计算机科学 2024-09-27 Piera Riccio , Georgina Curto , Nuria Oliver

Large-scale image datasets frequently contain identifiable or sensitive content, raising privacy risks when training models that may memorize and leak such information. We present Unsafe2Safe, a fully automated pipeline that detects…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Mih Dinh , SouYoung Jin

Text-to-image diffusion models can generate diverse content with flexible prompts, which makes them well-suited for customization through fine-tuning with a small amount of user-provided data. However, controllable fine-tuning that prevents…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Ziyao Zeng , Jingcheng Ni , Ruyi Liu , Alex Wong

In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily manipulated for identity impersonation, misinformation, or…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Linghui Shen , Mingyue Cui , Xingyi Yang

In the last two years, text-to-image diffusion models have become extremely popular. As their quality and usage increase, a major concern has been the need for better output control. In addition to prompt engineering, one effective method…

计算机视觉与模式识别 · 计算机科学 2024-11-25 Clément Bonnet , Ariel N. Lee , Franck Wertel , Antoine Tamano , Tanguy Cizain , Pablo Ducru

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior…

多媒体 · 计算机科学 2026-03-24 Luca Cazzaniga

Text-to-image models (T2I) offer a new level of flexibility by allowing users to guide the creative process through natural language. However, personalizing these models to align with user-provided visual concepts remains a challenging…

计算机视觉与模式识别 · 计算机科学 2024-06-06 Yoad Tewel , Rinon Gal , Gal Chechik , Yuval Atzmon

Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene internally within the generative model, but suffer from severe…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Xiangtao Meng , Yingkai Dong , Ning Yu , Li Wang , Zheng Li , Shanqing Guo

Text-to-image (T2I) models can be maliciously used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. Previous attacks largely depend on the availability of the diffusion…

密码学与安全 · 计算机科学 2025-05-27 Jiachen Ma , Yijiang Li , Zhiqing Xiao , Anda Cao , Jie Zhang , Chao Ye , Junbo Zhao

Modern Text-to-Image (T2I) Diffusion models have revolutionized image editing by enabling the generation of high-quality photorealistic images. While the de facto method for performing edits with T2I models is through text instructions,…

计算机视觉与模式识别 · 计算机科学 2024-11-07 Ashutosh Srivastava , Tarun Ram Menta , Abhinav Java , Avadhoot Jadhav , Silky Singh , Surgan Jandial , Balaji Krishnamurthy

Recent years have witnessed success in AIGC (AI Generated Content). People can make use of a pre-trained diffusion model to generate images of high quality or freely modify existing pictures with only prompts in nature language. More…

密码学与安全 · 计算机科学 2023-08-24 Yutong Wu , Jie Zhang , Florian Kerschbaum , Tianwei Zhang

Text-to-Image (T2I) diffusion models have rapidly advanced, enabling the generation of high-quality images that align closely with textual descriptions. However, this progress has also raised concerns about their misuse for propaganda and…

计算机视觉与模式识别 · 计算机科学 2024-12-25 Jaechul Roh , Andrew Yuan , Jinsong Mao

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…

计算机视觉与模式识别 · 计算机科学 2023-04-27 Patrick Schramowski , Manuel Brack , Björn Deiseroth , Kristian Kersting

Text-to-image (T2I) diffusion models have shown remarkable success in generating high-quality images from text prompts. Recent efforts extend these models to incorporate conditional images (e.g., canny edge) for fine-grained spatial…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Liheng Zhang , Lexi Pang , Hang Ye , Xiaoxuan Ma , Yizhou Wang

Text-to-Image (T2I) models have recently achieved remarkable success in generating images from textual descriptions. However, challenges still persist in accurately rendering complex scenes where actions and interactions form the primary…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Vatsal Malaviya , Agneet Chatterjee , Maitreya Patel , Yezhou Yang , Chitta Baral