English
Related papers

Related papers: Robust Concept Erasure in Diffusion Models: A Theo…

200 papers

With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 Yisu Liu , Jinyang An , Wanqian Zhang , Dayan Wu , Jingzi Gu , Zheng Lin , Weiping Wang

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yi Sun , Xinhao Zhong , Hongyan Li , Yimin Zhou , Junhao Li , Bin Chen , Xuan Wang

The rapid progress of visual autoregressive (VAR) models has brought new opportunities for text-to-image generation, but also heightened safety concerns. Existing concept erasure techniques, primarily designed for diffusion models, fail to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Xinhao Zhong , Yimin Zhou , Zhiqi Zhang , Junhao Li , Yi Sun , Bin Chen , Shu-Tao Xia , Xuan Wang , Ke Xu

Concept Erasure, which aims to prevent pretrained text-to-image models from generating content associated with semantic-harmful concepts (i.e., target concepts), is getting increased attention. State-of-the-art methods formulate this task…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Hongxu Chen , Zhen Wang , Taoran Mei , Lin Li , Bowei Zhu , Runshi Li , Long Chen

Removing undesired concepts from large-scale text-to-image (T2I) and text-to-video (T2V) diffusion models while preserving overall generative quality remains a major challenge, particularly as modern models such as Stable Diffusion v3,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Zhaoxin Fan , Nanxiang Jiang , Daiheng Gao , Shiji Zhou , Wenjun Wu

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

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

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-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Junyoung Seo , Wooseok Jang , Min-Seop Kwak , Hyeonsu Kim , Jaehoon Ko , Junho Kim , Jin-Hwa Kim , Jiyoung Lee , Seungryong Kim

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

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

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…

As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted characters or styles-has become essential for safety and compliance. Existing unlearning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Junyeong Ahn , Seojin Yoon , Sungyong Baik

Robust invisible watermarks are widely used to support copyright protection, content provenance, and accountability by embedding hidden signals designed to survive common post-processing operations. However, diffusion-based image editing…

Image and Video Processing · Electrical Eng. & Systems 2026-03-16 Qian Qi , Jiangyun Tang , Jim Lee , Emily Davis , Finn Carter

The remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social…

Computation and Language · Computer Science 2025-05-22 Zhiwen Li , Die Chen , Mingyuan Fan , Cen Chen , Yaliang Li , Yanhao Wang , Wenmeng Zhou

Current image steganography techniques are mainly focused on cover-based methods, which commonly have the risk of leaking secret images and poor robustness against degraded container images. Inspired by recent developments in diffusion…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Jiwen Yu , Xuanyu Zhang , Youmin Xu , Jian Zhang

Robust invisible watermarking embeds hidden information in images such that the watermark can survive various manipulations. However, the emergence of powerful diffusion-based image generation and editing techniques poses a new threat to…

Cryptography and Security · Computer Science 2025-11-17 Yunyi Ni , Ziyu Yang , Ze Niu , Emily Davis , Finn Carter

To prevent unauthorized use of text in images, Scene Text Removal (STR) has become a crucial task. It focuses on automatically removing text and replacing it with a natural, text-less background while preserving significant details such as…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Sanhita Pathak , Vinay Kaushik , Brejesh Lall

Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectral Cutoff Regeneration), a training-free, generation-time…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Yuta Matsuzaki , Seiichi Uchida , Shumpei Takezaki

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