English
Related papers

Related papers: PersGuard: Preventing Malicious Personalization vi…

200 papers

Personalized generative diffusion models, capable of synthesizing highly realistic images based on a few reference portraits, may pose substantial social, ethical, and legal risks via identity replication. Existing defense mechanisms rely…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Hanzhong Guo , Shen Nie , Chao Du , Tianyu Pang , Hao Sun , Chongxuan Li

We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privacy noise and the denoising capabilities of diffusion models.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Tao Huang , Jiayang Meng , Hong Chen , Guolong Zheng , Xu Yang , Xun Yi , Hua Wang

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

Cryptography and Security · Computer Science 2024-03-13 Hongwei Zhang , Xiaoyin Xu , Dongsheng An , Xianfeng Gu , Min Zhang

Text-to-image (T2I) models have demonstrated remarkable generative capabilities but remain vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery. While recent moderation efforts have introduced soft…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Zonglei Jing , Xiao Yang , Xiaoqian Li , Siyuan Liang , Aishan Liu , Mingchuan Zhang , Xianglong Liu

Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Jiangweizhi Peng , Zhiwei Tang , Gaowen Liu , Charles Fleming , Mingyi Hong

With the advancement of personalized image generation technologies, concerns about forgery attacks that infringe on portrait rights and privacy are growing. To address these concerns, protection perturbation algorithms have been developed…

Cryptography and Security · Computer Science 2025-08-11 Zelin Li , Ruohan Zong , Yifan Liu , Ruichen Yao , Yaokun Liu , Yang Zhang , Dong Wang

Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Vu Tuan Truong , Long Bao Le

Text-to-image (T2I) models can be maliciously used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. Previous attacks largely depend on the availability of the diffusion…

Cryptography and Security · Computer Science 2025-05-27 Jiachen Ma , Yijiang Li , Zhiqing Xiao , Anda Cao , Jie Zhang , Chao Ye , Junbo Zhao

Text-to-Image (T2I) models, represented by DALL$\cdot$E and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the carefully engineered prompts, which have become valuable…

Cryptography and Security · Computer Science 2026-01-22 Shiqian Zhao , Chong Wang , Yiming Li , Yihao Huang , Wenjie Qu , Siew-Kei Lam , Yi Xie , Kangjie Chen , Jie Zhang , Tianwei Zhang

Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Kaiyue Sun , Xian Liu , Yao Teng , Xihui Liu

Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Lei Zhang , Yu Pan , Bingrong Dai , Lin Wang

Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by the reference images. Despite promising identity fidelity…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yuxiang Wei , Zhilong Ji , Jinfeng Bai , Hongzhi Zhang , Lei Zhang , Wangmeng Zuo

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

Machine Learning · Computer Science 2020-08-11 Shuo Wang , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen , Tianle Chen

Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos for social expression. However, once these generations are shared on social media platforms…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Linyan Dai , Xinwei Zhang , Haoyang Li , Qingqing Ye , Haibo Hu

Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Chumeng Liang , Xiaoyu Wu , Yang Hua , Jiaru Zhang , Yiming Xue , Tao Song , Zhengui Xue , Ruhui Ma , Haibing Guan

The success of deep learning based face recognition systems has given rise to serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Existing methods for enhancing privacy fail to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Fahad Shamshad , Muzammal Naseer , Karthik Nandakumar

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

The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma: to prevent misuse, they are forced to damage the model's…

Cryptography and Security · Computer Science 2026-03-18 Lingyun Zhang , Yu Xie , Ping Chen

Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Lingzhi Yuan , Xinfeng Li , Chejian Xu , Guanhong Tao , Xiaojun Jia , Yihao Huang , Wei Dong , Yang Liu , Bo Li

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Machine Learning · Computer Science 2026-01-28 Divya Kothandaraman , Jaclyn Pytlarz