English
Related papers

Related papers: Minimalist Concept Erasure in Generative Models

200 papers

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Qinghong Yin , Yu Tian , Heming Yang , Xiang Chen , Xianlin Zhang , Xueming Li , Yue Zhan

Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Xinjie Li , Yang Zhao , Dong Wang , Yuan Chen , Li Cao , Xiaoping Liu

Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face significant limitations. While training-based methods are effective, their high computational…

Artificial Intelligence · Computer Science 2026-05-29 Yuhao Sun , Lingyun Yu , Haoxiang Xu , Fengyuan Miao , Zhuoer Xu , Hongtao Xie

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Ouxiang Li , Yuan Wang , Xinting Hu , Houcheng Jiang , Yanbin Hao , Fuli Feng

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

Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR models while maintaining overall generation quality remains an…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Haipeng Fan , Shiyuan Zhang , Baohunesitu , Zihang Guo , Huaiwen Zhang

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Machine Learning · Computer Science 2026-04-03 Lingjing Kong , Shaoan Xie , Guangyi Chen , Yuewen Sun , Xiangchen Song , Eric P. Xing , Kun Zhang

Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a critical challenge when fairness is a concern. We address…

Machine Learning · Computer Science 2025-08-19 Antoine Saillenfest , Pirmin Lemberger

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

Machine Learning · Computer Science 2025-05-28 Geyu Liang , Senne Michielssen , Salar Fattahi

In this work, we introduce Erasure of Language Memory (ELM), a principled approach to concept-level unlearning that operates by matching distributions defined by the model's own introspective classification capabilities. Our key insight is…

Computation and Language · Computer Science 2025-07-23 Rohit Gandikota , Sheridan Feucht , Samuel Marks , David Bau

The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure…

Machine Learning · Computer Science 2026-03-03 Xinwen Cheng , Jingyuan Zhang , Zhehao Huang , Yingwen Wu , Xiaolin Huang

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

Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Zixuan Fu , Yan Ren , Finn Carter , Chenyue Wang , Ze Niu , Dacheng Yu , Emily Davis , Bo Zhang

The rapid growth of text-to-image diffusion models has raised concerns about their potential misuse in generating harmful or unauthorized contents. To address these issues, several Concept Erasure methods have been proposed. However, most…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Kien Nguyen , Anh Tran , Cuong Pham

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

Text-to-Image diffusion models can produce undesirable content that necessitates concept erasure. However, existing methods struggle with under-erasure, leaving residual traces of targeted concepts, or over-erasure, mistakenly eliminating…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Yuyang Xue , Edward Moroshko , Feng Chen , Jingyu Sun , Steven McDonagh , Sotirios A. Tsaftaris

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

How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlearning', a novel paradigm that enables the targeted removal of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Kartik Thakral , Tamar Glaser , Tal Hassner , Mayank Vatsa , Richa Singh

Text-to-image diffusion models (DMs) inadvertently reproduce copyrighted styles and protected visual concepts, raising legal and ethical concerns. Concept erasure has emerged as a safeguard, aiming to selectively suppress such concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Jiaqi Liu , Lan Zhang , Xiaoyong Yuan

Recently, several methods have leveraged deep generative modeling to produce example-based explanations of image classifiers. Despite producing visually stunning results, these methods are largely disconnected from classical explainability…

Machine Learning · Computer Science 2025-09-11 Philipp Vaeth , Alexander M. Fruehwald , Benjamin Paassen , Magda Gregorova