English
Related papers

Related papers: When Are Concepts Erased From Diffusion Models?

200 papers

Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Xiaoyu Ye , Songjie Cheng , Yongtao Wang , Yajiao Xiong , Yishen Li

Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles. In response, existing approaches…

Machine Learning · Computer Science 2024-02-12 Mengnan Zhao , Lihe Zhang , Tianhang Zheng , Yuqiu Kong , Baocai Yin

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yi Sun , Xinhao Zhong , Hongyan Li , Yimin Zhou , Junhao Li , Bin Chen , Xuan Wang

Text-to-image diffusion models have shown an impressive ability to generate high-quality images from input textual descriptions. However, concerns have been raised about the potential for these models to create content that infringes on…

Computer Vision and Pattern Recognition · Computer Science 2025-01-16 Tingxu Han , Weisong Sun , Yanrong Hu , Chunrong Fang , Yonglong Zhang , Shiqing Ma , Tao Zheng , Zhenyu Chen , Zhenting Wang

Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled reproduction of sensitive, copyrighted, or harmful imagery poses…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Yiwei Xie , Ping Liu , Zheng Zhang

Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Arian Komaei Koma , Seyed Amir Kasaei , Ali Aghayari , AmirMahdi Sadeghzadeh , Mohammad Hossein Rohban

Diffusion models have demonstrated remarkable capability in generating high-quality visual content from textual descriptions. However, since these models are trained on large-scale internet data, they inevitably learn undesirable concepts,…

Machine Learning · Computer Science 2025-02-18 Anh Bui , Khanh Doan , Trung Le , Paul Montague , Tamas Abraham , Dinh Phung

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Lexiang Xiong , Chengyu Liu , Jingwen Ye , Yan Liu , Yuecong Xu

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Chao Huang , Susan Liang , Yunlong Tang , Yapeng Tian , Anurag Kumar , Chenliang Xu

Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image quality, rely on brittle adversarial losses, or demand…

Machine Learning · Computer Science 2025-11-11 Abhiram Kusumba , Maitreya Patel , Kyle Min , Changhoon Kim , Chitta Baral , Yezhou Yang

The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Mengyao Lyu , Yuhong Yang , Haiwen Hong , Hui Chen , Xuan Jin , Yuan He , Hui Xue , Jungong Han , Guiguang Ding

For the last decade, there has been a push to use multi-dimensional (latent) spaces to represent concepts; and yet how to manipulate these concepts or reason with them remains largely unclear. Some recent methods exploit multiple latent…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Lorenzo Olearo , Giorgio Longari , Simone Melzi , Alessandro Raganato , Rafael Peñaloza

Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Ziqiang Li , Jun Li , Lizhi Xiong , Zhangjie Fu , Zechao Li

Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the target concept is absent from generated frames, treating…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yiwei Xie , Zheng Zhang , Ping Liu

Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. Although various techniques have been proposed to mitigate unwanted influences…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Jing Wu , Trung Le , Munawar Hayat , Mehrtash Harandi

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

Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Chao Gong , Kai Chen , Zhipeng Wei , Jingjing Chen , Yu-Gang Jiang

Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yi Huang , Jiancheng Huang , Yifan Liu , Mingfu Yan , Jiaxi Lv , Jianzhuang Liu , Wei Xiong , He Zhang , Liangliang Cao , Shifeng Chen

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

Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Daiheng Gao , Shilin Lu , Shaw Walters , Wenbo Zhou , Jiaming Chu , Jie Zhang , Bang Zhang , Mengxi Jia , Jian Zhao , Zhaoxin Fan , Weiming Zhang