English
Related papers

Related papers: Do Protective Perturbations Really Protect Portrai…

200 papers

Deepfakes pose severe threats of visual misinformation to our society. One representative deepfake application is face manipulation that modifies a victim's facial attributes in an image, e.g., changing her age or hair color. The…

Cryptography and Security · Computer Science 2022-10-04 Zheng Li , Ning Yu , Ahmed Salem , Michael Backes , Mario Fritz , Yang Zhang

Previous work has suggested that preprocessing images through lossy compression can defend against adversarial perturbations, but comprehensive attack evaluations have been lacking. In this paper, we construct strong white-box and adaptive…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Samuel Räber , Till Aczel , Andreas Plesner , Roger Wattenhofer

Recent advances in GAN and diffusion models have significantly improved the realism and controllability of facial deepfake manipulation, raising serious concerns regarding privacy, security, and identity misuse. Proactive defenses attempt…

Cryptography and Security · Computer Science 2026-04-03 Yue Li , Linying Xue , Kaiqing Lin , Hanyu Quan , Dongdong Lin , Hui Tian , Hongxia Wang , Bin Wang

Camera sensors are increasingly being combined with machine learning to perform various tasks such as intelligent surveillance. Due to its computational complexity, most of these machine learning algorithms are offloaded to the cloud for…

Computer Vision and Pattern Recognition · Computer Science 2022-08-29 Sander De Coninck , Wei-Cheng Wang , Sam Leroux , Pieter Simoens

In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily manipulated for identity impersonation, misinformation, or…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Linghui Shen , Mingyue Cui , Xingyi Yang

Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse…

Graphics · Computer Science 2025-06-03 Yuan Gan , Jiaxu Miao , Yunze Wang , Yi Yang

Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Namhyuk Ahn , Wonhyuk Ahn , KiYoon Yoo , Daesik Kim , Seung-Hun Nam

The success of deep face recognition (FR) systems has raised serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Previous studies proposed introducing imperceptible adversarial noises…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Minghui Li , Jiangxiong Wang , Hao Zhang , Ziqi Zhou , Shengshan Hu , Xiaobing Pei

Protecting sensitive information against data exploiting attacks is an emerging research area in data mining. Over the past, several different methods have been introduced to protect individual privacy from such attacks while maximizing…

Cryptography and Security · Computer Science 2021-07-29 Hung Nguyen , Di Zhuang , Pei-Yuan Wu , Morris Chang

As the privacy risks posed by camera surveillance and facial recognition have grown, so has the research into privacy preservation algorithms. Among these, visual privacy preservation algorithms attempt to impart bodily privacy to subjects…

Computer Vision and Pattern Recognition · Computer Science 2023-01-13 Sophie Noiret , Siddharth Ravi , Martin Kampel , Francisco Florez-Revuelta

Recent image protection mechanisms such as Glaze and Nightshade introduce imperceptible, adversarially designed perturbations intended to disrupt downstream text-to-image generative models. While their empirical effectiveness is known, the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Michael R. Martin , Garrick Chan , Kwan-Liu Ma

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Machine Learning · Computer Science 2021-08-17 Xue Yang , Yan Feng , Weijun Fang , Jun Shao , Xiaohu Tang , Shu-Tao Xia , Rongxing Lu

The misuse of deep learning-based facial manipulation poses a significant threat to civil rights. To prevent this fraud at its source, proactive defense has been proposed to disrupt the manipulation process by adding invisible adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Zuomin Qu , Wei Lu , Xiangyang Luo , Qian Wang , Xiaochun Cao

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Junjie Cao , Kaizhou Li , Xinchun Yu , Hongxiang Li , Xiaoping Zhang

The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public. Even though differential privacy (DP) is a widely accepted…

Cryptography and Security · Computer Science 2023-06-21 Hanyu Xue , Bo Liu , Ming Ding , Tianqing Zhu , Dayong Ye , Li Song , Wanlei Zhou

Pose-driven human image animation has achieved tremendous progress, enabling the generation of vivid and realistic human videos from just one single photo. However, it conversely exacerbates the risk of image misuse, as attackers may use…

Cryptography and Security · Computer Science 2025-02-25 Jiachen Zhou , Mingsi Wang , Tianlin Li , Guozhu Meng , Kai Chen

Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to subtle adversarial perturbations, prompting the development of many advanced adversarial defense methods aimed at mitigating adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Linyu Tang , Lei Zhang

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

Diffusion-based face swapping achieves state-of-the-art performance, yet it also exacerbates the potential harm of malicious face swapping to violate portraiture right or undermine personal reputation. This has spurred the development of…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Yilong Huang , Songze Li

Adversarially perturbed images of text can cause sophisticated OCR systems to produce misleading or incorrect transcriptions from seemingly invisible changes to humans. Some of these perturbations even survive physical capture, posing…

Machine Learning · Computer Science 2025-11-21 Bhagyesh Kumar , A S Aravinthakashan , Akshat Satyanarayan , Ishaan Gakhar , Ujjwal Verma