The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on social media. Several attempts have been made to protect individuals from being identified by unauthorized FR systems utilizing adversarial attacks to generate encrypted face images. However, existing methods suffer from poor visual quality or low attack success rates, which limit their utility. Recently, diffusion models have achieved tremendous success in image generation. In this work, we ask: can diffusion models be used to generate adversarial examples to improve both visual quality and attack performance? We propose DiffProtect, which utilizes a diffusion autoencoder to generate semantically meaningful perturbations on FR systems. Extensive experiments demonstrate that DiffProtect produces more natural-looking encrypted images than state-of-the-art methods while achieving significantly higher attack success rates, e.g., 24.5% and 25.1% absolute improvements on the CelebA-HQ and FFHQ datasets.
Flux-Guard: Facial Identity Protection using diffusion models
School of Cyberspace Security, Beijing University of Posts and Telecommunications(北京邮电大学网络空间安全学院);Nanjing University of Aeronautics and Astronautics(南京航空航天大学)
Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models
School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);China Mobile Information Technology Co., Ltd.(中国移动信息科技有限公司);State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation Chinese Academy of Sciences (CASIA)(多模态人工智能系统国家重点实验室(MAIS)、智能感知与计算研究中心(CRIPAC)、中国科学院自动化研究所(CASIA))
Face De-identification: State-of-the-art Methods and Comparative Studies
The Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University(上海交通大学图像通信与网络工程研究所);Australian Artificial Intelligence Institute(澳大利亚人工智能研究所);University of Technology Sydney(悉尼科技大学);Data61, CSIRO(联邦科学与工业研究组织Data61研究院);University of Missouri-Kansas City(密苏里大学堪萨斯城分校)
Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer
Huazhong University of Science and Technology(华中科技大学);National Engineering Research Center for Big Data Technology and System(国家大数据技术与系统工程研究中心);Hubei Engineering Research Center on Big Data Security(湖北省大数据安全工程研究中心);Deakin University(迪肯大学)
k-Same-Siamese-GAN: k-Same Algorithm with Generative Adversarial Network for Facial Image De-identification with Hyperparameter Tuning and Mixed Precision Training
Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection
School of Computer Science;Engineering, Sun Yat-sen University Guangzhou China;State Key Laboratory of Mathematical Engineering;Engineering, Sun Yat-sen University
A Survey on Facial Image Privacy Preservation in Cloud-Based Services
Nanyang Technological University(南洋理工大学);School of Cyber Science and Engineering, Wuhan University(武汉大学网络安全学院);College of Electrical Engineering, Zhejiang University(浙江大学电气工程学院)
PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors
Institute of Information Engineering, Chinese Academy of Sciences(信息工程研究所,中国科学院);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);BraneMatrix AI;School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University(中山大学深圳校区计算机科学与技术学院)
DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy
University of Electronic Science and Technology of China(电子科技大学);CISPA Helmholtz Center for Information Security(信息安全赫尔姆霍茨中心);The Chinese University of Hong Kong(香港中文大学)
Transferable Adversarial Facial Images for Privacy Protection
School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件学院);School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间安全学院)
TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer
Zhejiang University(浙江大学);Alibaba Group(阿里巴巴集团);Institute of High Performance Computing (IHPC)(高性能计算研究所);Centre for Frontier AI Research (CFAR)(前沿人工智能研究中心)
An Attack on Facial Soft-biometric Privacy Enhancement
Hochschule Darmstadt(达姆施塔特应用技术大学);Fraunhofer Institute for Computer Graphics Research(弗劳恩霍夫计算机图形学研究所);Norwegian University of Science and Technology(挪威科技大学);University of Ljubljana(卢布尔雅那大学)
ZJU-Hangzhou Global Scientific and Technological Innovation Center(浙江大学杭州国际科创中心);Alibaba Group(阿里巴巴集团);College of Computer Science and Electronic Engineering, Hunan University(湖南大学计算机与电子工程学院);School of Cyber Science and Engineering, Wuhan University(武汉大学网络空间安全学院);School of Cyber Science and Technology, Zhejiang University(浙江大学网络空间安全学院)
Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University(西北工业大学人工智慧、光学与电子学院(iOPEN));The University of Hong Kong(香港大学);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院(TeleAI))
本文提出 Adv-CPG 框架,首次将面部对抗攻击引入定制肖像生成,通过轻量级局部 ID 加密器、加密增强器和多模态图像定制器实现隐私保护与细粒度个性化生成,实验表明其攻击成功率优于现有方法。