English
Related papers

Related papers: FADE: Adversarial Concept Erasure in Flow Models

200 papers

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Decheng Liu , Xijun Wang , Chunlei Peng , Nannan Wang , Ruiming Hu , Xinbo Gao

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Machine Learning · Computer Science 2024-07-01 Lucas Beerens , Catherine F. Higham , Desmond J. Higham

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

Generating multiple new concepts remains a challenging problem in the text-to-image task. Current methods often overfit when trained on a small number of samples and struggle with attribute leakage, particularly for class-similar subjects…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Gia-Nghia Tran , Quang-Huy Che , Trong-Tai Dam Vu , Bich-Nga Pham , Vinh-Tiep Nguyen , Trung-Nghia Le , Minh-Triet Tran

We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward pass formulates image corruption via a physically motivated…

Graphics · Computer Science 2026-05-05 Grzegorz Gruszczynski , Jakub Meixner , Michal Jan Wlodarczyk , Przemyslaw Musialski

The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on social media. Several attempts have been made to protect…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Jiang Liu , Chun Pong Lau , Zhongliang Guo , Yuxiang Guo , Zhaoyang Wang , Rama Chellappa

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…

Machine Learning · Computer Science 2025-04-04 Nora Belrose , David Schneider-Joseph , Shauli Ravfogel , Ryan Cotterell , Edward Raff , Stella Biderman

Robust invisible watermarking schemes aim to embed hidden information into images such that the watermark survives common manipulations. However, powerful diffusion-based image generation and editing techniques now pose a new threat to…

Cryptography and Security · Computer Science 2026-02-25 Fan Guo , Jiyu Kang , Qi Ming , Emily Davis , Finn Carter

The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Joonsung Jeon , Woo Jae Kim , Suhyeon Ha , Sooel Son , Sung-eui Yoon

The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Eric Zhang , Kai Wang , Xingqian Xu , Zhangyang Wang , Humphrey Shi

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

Robust invisible watermarking aims to embed hidden messages into images such that they survive various manipulations while remaining imperceptible. However, powerful diffusion-based image generation and editing models now enable realistic…

Cryptography and Security · Computer Science 2025-11-11 Wenkai Fu , Finn Carter , Yue Wang , Emily Davis , Bo Zhang

Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Viet Nguyen , Vishal M. Patel

Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Rohit Gandikota , Hadas Orgad , Yonatan Belinkov , Joanna Materzyńska , David Bau

Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Hoigi Seo , Byung Hyun Lee , Jaehyun Cho , Sungjin Lim , Se Young Chun

Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures (e.g., Flux), this task remains under-explored in the recent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Nanxiang Jiang , Zhaoxin Fan , Baisen Wang , Daiheng Gao , Junhang Cheng , Jifeng Guo , Yalan Qin , Yeying Jin , Hongwei Zheng , Faguo Wu , Wenjun Wu

As face recognition becomes more widespread in government and commercial services, its potential misuse raises serious concerns about privacy and civil rights. To counteract this threat, various anti-facial recognition techniques have been…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Youngjin Kwon , Xiao Zhang

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

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

As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent content. Existing methods for concept removal generally guide the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Lingyun Zhang , Yu Xie , Yanwei Fu , Ping Chen
‹ Prev 1 3 4 5 6 7 10 Next ›