English
Related papers

Related papers: TRCE: Towards Reliable Malicious Concept Erasure i…

200 papers

To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Ping Liu , Chi Zhang

The rapid expansion of large-scale text-to-image diffusion models has raised growing concerns regarding their potential misuse in creating harmful or misleading content. In this paper, we introduce MACE, a finetuning framework for the task…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Shilin Lu , Zilan Wang , Leyang Li , Yanzhu Liu , Adams Wai-Kin Kong

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 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

Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Hongguang Zhu , Yunchao Wei , Mengyu Wang , Siyu Jiao , Yan Fang , Jiannan Huang , Yao Zhao

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

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

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

Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models by selectively unlearning undesirable concepts. The common principle of previous works to remove a specific…

Machine Learning · Computer Science 2025-05-26 Anh Bui , Trang Vu , Long Vuong , Trung Le , Paul Montague , Tamas Abraham , Junae Kim , Dinh Phung

The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To…

Cryptography and Security · Computer Science 2025-05-01 Jonas Henry Grebe , Tobias Braun , Marcus Rohrbach , Anna Rohrbach

Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Yiwei Xie , Ping Liu , Zheng Zhang

Recent advancements in Text-to-Image (T2I) diffusion models have demonstrated impressive success in generating high-quality images with zero-shot generalization capabilities. Yet, current models struggle to closely adhere to prompt…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Hyun Kang , Dohae Lee , Myungjin Shin , In-Kwon Lee

Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Zhiqi Zhang , Xinhao Zhong , Yi Sun , Shuoyang Sun , Bin Chen , Shu-Tao Xia , Xuan Wang

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

Studies have been conducted to prevent specific concepts from being generated from pretrained text-to-image generative models, achieving concept erasure in various ways. However, the performance evaluation of these studies is still largely…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Masane Fuchi , Tomohiro Takagi

Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Shristi Das Biswas , Arani Roy , Kaushik Roy

Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Qinghui Gong

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

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Zhengbo Zhang , Zhigang Tu , Junsong Yuan , De Wen Soh , Bo Du

Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful capabilities. In this paper, we investigate the proactive…

Cryptography and Security · Computer Science 2025-02-06 Yixin Wu , Ning Yu , Michael Backes , Yun Shen , Yang Zhang