English
Related papers

Related papers: STEREO: A Two-Stage Framework for Adversarially Ro…

200 papers

Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure methods aim to restrict edits to the spatial region occupied by the target concept.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zhuan Shi , Alireza Dehghanpour Farashah , Rik de Vries , Golnoosh Farnadi

Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Uichan Lee , Jeonghyeon Kim , Sangheum Hwang

Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising…

Machine Learning · Computer Science 2025-03-19 Yongliang Wu , Shiji Zhou , Mingzhuo Yang , Lianzhe Wang , Heng Chang , Wenbo Zhu , Xinting Hu , Xiao Zhou , Xu Yang

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Yi Sun , Zhiqi Zhang , Xinhao Zhong , Yimin Zhou , Shuoyang Sun , Bin Chen , Shu-Tao Xia , Ke Xu

Text-to-image diffusion models (T2I DMs), represented by Stable Diffusion, which generate highly realistic images based on textual input, have been widely used, but their flexibility also makes them prone to misuse for producing harmful or…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Chaoshuo Zhang , Chenhao Lin , Zhengyu Zhao , Le Yang , Qian Wang , Chao Shen

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…

Computer Vision and Pattern Recognition · Computer Science 2022-01-04 Yexin Duan , Junhua Zou , Xingyu Zhou , Wu Zhang , Jin Zhang , Zhisong Pan

Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed as the "implicit concepts", could be unintentionally learned during training and then be…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Zhili Liu , Kai Chen , Yifan Zhang , Jianhua Han , Lanqing Hong , Hang Xu , Zhenguo Li , Dit-Yan Yeung , James Kwok

Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both…

Recent efforts on scene text erasing have shown promising results. However, existing methods require rich yet costly label annotations to obtain robust models, which limits the use for practical applications. To this end, we study an…

Computer Vision and Pattern Recognition · Computer Science 2022-04-28 Gangwei Jiang , Shiyao Wang , Tiezheng Ge , Yuning Jiang , Ying Wei , Defu Lian

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Jie Ren , Kangrui Chen , Yingqian Cui , Shenglai Zeng , Hui Liu , Yue Xing , Jiliang Tang , Lingjuan Lyu

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…

Machine Learning · Computer Science 2026-05-12 Nicola Novello , Andrea M. Tonello

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Feng Han , Kai Chen , Chao Gong , Zhipeng Wei , Jingjing Chen , Yu-Gang Jiang

Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful content. This has fostered a dynamic interplay between the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Qianlong Xiang , Miao Zhang , Haoyu Zhang , Kun Wang , Junhui Hou , Liqiang Nie

As Text-to-Image models continue to evolve, so does the risk of generating unsafe, copyrighted, or privacy-violating content. Existing safety interventions - ranging from training data curation and model fine-tuning to inference-time…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Shristi Das Biswas , Arani Roy , Kaushik Roy

Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work)…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jiahang Tu , Qian Feng , Jiahua Dong , Hanbin Zhao , Chao Zhang , Nicu Sebe , Hui Qian

Remarkable progress in text-to-image diffusion models has brought a major concern about potentially generating images on inappropriate or trademarked concepts. Concept erasing has been investigated with the goals of deleting target concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Byung Hyun Lee , Sungjin Lim , Seunggyu Lee , Dong Un Kang , Se Young Chun

As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted characters or styles-has become essential for safety and compliance. Existing unlearning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Junyeong Ahn , Seojin Yoon , Sungyong Baik

Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Anubhav Jain , Yuya Kobayashi , Takashi Shibuya , Yuhta Takida , Nasir Memon , Julian Togelius , Yuki Mitsufuji

Concept erasure is extensively utilized in image generation to prevent text-to-image models from generating undesired content. Existing methods can effectively erase narrow concepts that are specific and concrete, such as distinct…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuze Cai , Jiahao Lu , Hongxiang Shi , Yichao Zhou , Hong Lu

In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly these approaches remove the target concept from the model.…

Machine Learning · Computer Science 2025-11-10 Kevin Lu , Nicky Kriplani , Rohit Gandikota , Minh Pham , David Bau , Chinmay Hegde , Niv Cohen