English
Related papers

Related papers: ACE: Anti-Editing Concept Erasure in Text-to-Image…

200 papers

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

Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications. However, since they are highly data-driven, relying on billion-sized datasets randomly…

Editing images with diffusion models under strict training-free constraints remains a significant challenge. While recent optimisation-based methods achieve strong zero-shot edits from text, they struggle to preserve identity and capture…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Niki Foteinopoulou , Ignas Budvytis , Stephan Liwicki

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

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

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Chao Huang , Susan Liang , Yunlong Tang , Yapeng Tian , Anurag Kumar , Chenliang Xu

Explicit Caption Editing (ECE) -- refining reference image captions through a sequence of explicit edit operations (e.g., KEEP, DETELE) -- has raised significant attention due to its explainable and human-like nature. After training with…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 Zhen Wang , Xinyun Jiang , Jun Xiao , Tao Chen , Long Chen

Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data. To mitigate this, concept ablation techniques have been explored to limit the generation…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Matan Rusanovsky , Shimon Malnick , Amir Jevnisek , Ohad Fried , Shai Avidan

Text-to-image (T2I) models face significant safety risks from adversarial induction, yet current concept erasure methods often cause collateral damage to benign attributes when suppressing selected neurons entirely. This occurs because…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Chuancheng Shi , Wenhua Wu , Fei Shen , Xiaogang Zhu , Kun Hu , Zhiyong Wang

Text-to-image diffusion models rely on text embeddings from a pre-trained text encoder, but these embeddings remain fixed across all diffusion timesteps, limiting their adaptability to the generative process. We propose Diffusion Adaptive…

Machine Learning · Computer Science 2025-10-29 Byeonghu Na , Minsang Park , Gyuwon Sim , Donghyeok Shin , HeeSun Bae , Mina Kang , Se Jung Kwon , Wanmo Kang , Il-Chul Moon

Diffusion models have demonstrated impressive performance in text-guided image generation. Current methods that leverage the knowledge of these models for image editing either fine-tune them using the input image (e.g., Imagic) or…

Computer Vision and Pattern Recognition · Computer Science 2023-11-09 Zhongping Zhang , Jian Zheng , Jacob Zhiyuan Fang , Bryan A. Plummer

Text-to-image diffusion models have emerged as an evolutionary for producing creative content in image synthesis. Based on the impressive generation abilities of these models, instruction-guided diffusion models can edit images with simple…

Cryptography and Security · Computer Science 2024-08-21 Ruoxi Chen , Haibo Jin , Yixin Liu , Jinyin Chen , Haohan Wang , Lichao Sun

Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal…

Artificial Intelligence · Computer Science 2025-10-21 Tong Zhang , Ru Zhang , Jianyi Liu , Zhen Yang , Gongshen Liu

Text-to-image diffusion models sometimes depict blended concepts in the generated images. One promising use case of this effect would be the nonword-to-image generation task which attempts to generate images intuitively imaginable from a…

Multimedia · Computer Science 2024-11-07 Chihaya Matsuhira , Marc A. Kastner , Takahiro Komamizu , Takatsugu Hirayama , Ichiro Ide

Inspired by the software industry's practice of offering different editions or versions of a product tailored to specific user groups or use cases, we propose a novel task, namely, training-free editioning, for text-to-image models.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Jinqi Wang , Yunfei Fu , Zhangcan Ding , Bailin Deng , Yu-Kun Lai , Yipeng Qin

Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Junseok Ko , Jungwoo Kim , Jong-Seok Lee

Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where the source image is first corrupted into an editable…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yanghao Wang , Zhen Wang , Long Chen

With the increasing versatility of text-to-image diffusion models, the ability to selectively erase undesirable concepts (e.g., harmful content) has become indispensable. However, existing concept erasure approaches primarily focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Yongwoo Kim , Sungmin Cha , Hyunsoo Kim , Jaewon Lee , Donghyun Kim

The recent success of text-to-image generation diffusion models has also revolutionized semantic image editing, enabling the manipulation of images based on query/target texts. Despite these advancements, a significant challenge lies in the…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Zuopeng Yang , Tianshu Chu , Xin Lin , Erdun Gao , Daqing Liu , Jie Yang , Chaoyue Wang

Recent research has seen significant interest in methods for concept removal and targeted forgetting in text-to-image diffusion models. In this paper, we conduct a comprehensive white-box analysis showing the vulnerabilities in existing…

Machine Learning · Computer Science 2024-12-13 Aakash Sen Sharma , Niladri Sarkar , Vikram Chundawat , Ankur A Mali , Murari Mandal