English
Related papers

Related papers: Robust Concept Erasure Using Task Vectors

200 papers

With the rise of large, publicly-available text-to-image diffusion models, text-guided real image editing has garnered much research attention recently. Existing methods tend to either rely on some form of per-instance or per-task…

Computer Vision and Pattern Recognition · Computer Science 2022-11-16 Adham Elarabawy , Harish Kamath , Samuel Denton

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ruidong Chen , Honglin Guo , Lanjun Wang , Chenyu Zhang , Weizhi Nie , An-An Liu

Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Masane Fuchi , Tomohiro Takagi

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

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Seunghoo Hong , Juhun Lee , Simon S. Woo

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

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

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

The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt…

Computer Vision and Pattern Recognition · Computer Science 2023-12-20 Shweta Mahajan , Tanzila Rahman , Kwang Moo Yi , Leonid Sigal

Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Die Chen , Zhiwen Li , Cen Chen , Yuexiang Xie , Xiaodan Li , Jinyan Ye , Yingda Chen , Yaliang Li

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

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-driven video editing enables users to modify video content only using text queries. While existing methods can modify video content if explicit descriptions of editing targets with precise spatial locations and temporal boundaries are…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Yiqing Shen , Chenjia Li , Mathias Unberath

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

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

Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which leads to various ethical and business risks. Specifically,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Die Chen , Zhiwen Li , Mingyuan Fan , Cen Chen , Wenmeng Zhou , Yanhao Wang , Yaliang Li

Generative models, particularly diffusion-based text-to-image (T2I) models, have demonstrated astounding success. However, aligning them to avoid generating content with unacceptable concepts (e.g., offensive or copyrighted content, or…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Anudeep Das , Gurjot Singh , Prach Chantasantitam , N. Asokan

The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, concept erasure (defense) methods have been…

Machine Learning · Computer Science 2025-10-06 Alex D. Richardson , Kaicheng Zhang , Lucas Beerens , Dongdong Chen

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Yimeng Zhang , Xin Chen , Jinghan Jia , Yihua Zhang , Chongyu Fan , Jiancheng Liu , Mingyi Hong , Ke Ding , Sijia Liu

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