English
Related papers

Related papers: FADE: Adversarial Concept Erasure in Flow Models

200 papers

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

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

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

Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a critical challenge when fairness is a concern. We address…

Machine Learning · Computer Science 2025-08-19 Antoine Saillenfest , Pirmin Lemberger

Erase inpainting, or object removal, aims to precisely remove target objects within masked regions while preserving the overall consistency of the surrounding content. Despite diffusion-based methods have made significant strides in the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Yi Liu , Hao Zhou , Wenxiang Shang , Ran Lin , Benlei Cui

The recent proliferation of diffusion models has made style mimicry effortless, enabling users to imitate unique artistic styles without authorization. In deployed platforms, this raises copyright and intellectual-property risks and calls…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Tong Zhang , Ru Zhang , Jianyi Liu

Motivated by ethical and legal concerns, the scientific community is actively developing methods to limit the misuse of Text-to-Image diffusion models for reproducing copyrighted, violent, explicit, or personal information in the generated…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Vitali Petsiuk , Kate Saenko

Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Gaozheng Pei , Shaojie Lyu , Gong Chen , Ke Ma , Qianqian Xu , Yingfei Sun , Qingming Huang

While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Severi Rissanen , Markus Heinonen , Arno Solin

Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jie Zhang , Shuai Dong , Shiguang Shan , Xilin Chen

Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods either rely on costly fine-tuning or apply coarse semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Ning Han , Zhenyu Ge , Feng Han , Yuhua Sun , Chengqing Li , Jingjing Chen

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

The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the clean images through the reverse process. Due to the lack of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Gaozheng Pei , Ke Ma , Yingfei Sun , Qianqian Xu , Qingming Huang

We present GIFT: a {G}radient-aware {I}mmunization technique to defend diffusion models against malicious {F}ine-{T}uning while preserving their ability to generate safe content. Existing safety mechanisms like safety checkers are easily…

Cryptography and Security · Computer Science 2025-07-21 Amro Abdalla , Ismail Shaheen , Dan DeGenaro , Rupayan Mallick , Bogdan Raita , Sarah Adel Bargal

Diffusion models have achieved remarkable results in generating high-quality, diverse, and creative images. However, when it comes to text-based image generation, they often fail to capture the intended meaning presented in the text. For…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Kota Sueyoshi , Takashi Matsubara

Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…

Machine Learning · Computer Science 2023-10-10 Minh Pham , Kelly O. Marshall , Niv Cohen , Govind Mittal , Chinmay Hegde

Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yiqing Shi , Yiren Song , Mike Zheng Shou

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

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Computation and Language · Computer Science 2023-05-09 Zecheng Tang , Pinzheng Wang , Keyan Zhou , Juntao Li , Ziqiang Cao , Min Zhang

State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Yiting Qu , Xinyue Shen , Xinlei He , Michael Backes , Savvas Zannettou , Yang Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›