English
Related papers

Related papers: Circumventing Concept Erasure Methods For Text-to-…

200 papers

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

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

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

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

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-04 Nan Liu , Yilun Du , Shuang Li , Joshua B. Tenenbaum , Antonio Torralba

Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Hazarapet Tunanyan , Dejia Xu , Shant Navasardyan , Zhangyang Wang , Humphrey Shi

Concept erasure is the task of erasing information about a concept (e.g., gender or race) from a representation set while retaining the maximum possible utility -- information from original representations. Concept erasure is useful in…

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remove or filter…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Jordan Vice , Naveed Akhtar , Mubarak Shah , Richard Hartley , Ajmal Mian

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

Text-to-image generation has shown remarkable progress with the emergence of diffusion models. However, these models often generate factually inconsistent images, failing to accurately reflect the factual information and common sense…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Youngsun Lim , Hyunjung Shim

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

Concerns about text-to-image (T2I) generative models infringing on privacy, copyright, and safety have led to the development of concept erasure techniques (CETs). The goal of an effective CET is to prohibit the generation of undesired…

Machine Learning · Computer Science 2025-09-23 Shaswati Saha , Sourajit Saha , Manas Gaur , Tejas Gokhale

This paper addresses the societal concerns arising from large-scale text-to-image diffusion models for generating potentially harmful or copyrighted content. Existing models rely heavily on internet-crawled data, wherein problematic…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Sanghyun Kim , Seohyeon Jung , Balhae Kim , Moonseok Choi , Jinwoo Shin , Juho Lee

Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work)…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jiahang Tu , Qian Feng , Jiahua Dong , Hanbin Zhao , Chao Zhang , Nicu Sebe , Hui Qian

Concept erasure, which fine-tunes diffusion models to remove undesired or harmful visual concepts, has become a mainstream approach to mitigating unsafe or illegal image generation in text-to-image models.However, existing removal methods…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Hao Chen , Yiwei Wang , Songze Li

In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Muxi Chen , Yi Liu , Jian Yi , Changran Xu , Qiuxia Lai , Hongliang Wang , Tsung-Yi Ho , Qiang Xu

While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Nupur Kumari , Bingliang Zhang , Richard Zhang , Eli Shechtman , Jun-Yan Zhu

Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…

Machine Learning · Computer Science 2023-06-21 Abhinav Kumar , Chenhao Tan , Amit Sharma

The rapid proliferation of multimodal generative models has sparked critical discussions on their reliability, fairness and potential for misuse. While text-to-image models excel at producing high-fidelity, user-guided content, they often…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Jordan Vice , Naveed Akhtar , Leonid Sigal , Richard Hartley , Ajmal Mian

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