Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original images. The key idea is that these protected images prevent face manipulation by causing the manipulation model to produce a predefined manipulation target (uniformly colored output image in our case) instead of the actual manipulation. In addition, we propose to leverage differentiable compression approximation, hence making generated perturbations robust to common image compression. In order to prevent against multiple manipulation methods simultaneously, we further propose a novel attention-based fusion of manipulation-specific perturbations. Compared to traditional adversarial attacks that optimize noise patterns for each image individually, our generalized model only needs a single forward pass, thus running orders of magnitude faster and allowing for easy integration in image processing stacks, even on resource-constrained devices like smartphones.
AutoFFS: Adversarial Deformations for Facial Feminization Surgery Planning
Department of Biomedical Engineering, University of Basel（巴塞尔大学生物医学工程系）；Department of Oral and Cranio-Maxillofacial Surgery, University Hospital Basel（巴塞尔大学口腔和颅面外科系）
Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）；Shenzhen Key Laboratory of Media Security（深圳媒体安全重点实验室）；SZU-AFS Joint Innovation Center for AI Technology（深圳大学-腾讯优图联合创新中心）；Shenzhen University（深圳大学）；School of Electronic and Computer Engineering（电子与计算机工程学院）；Peking Univerisity（北京大学）；Tencent Youtu Lab（腾讯优图实验室）
Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection
Shenzhen Technology University（深圳技术大学）；Singapore Institute of Technology（新加坡理工学院）；The University of Hong Kong（香港大学）；Nanyang Technological University（南洋理工大学）
Face to Purchase: Predicting Consumer Choices with Structured Facial and Behavioral Traits Embedding
University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）；Raiz Invest Limited（Raiz投资有限公司）；Singapore Management University（新加坡管理大学）
Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
Xidian University（西安电子科技大学）；The University of Sydney（悉尼大学）；Shanghai Jiao Tong University（上海交通大学）；State Key Laboratory of Integrated Services Networks（集成服务网络国家重点实验室）
Attributes Shape the Embedding Space of Face Recognition Models
Department of Mathematical Sciences, Politecnico di Torino, Turin, Italy（波兰理工学院数学科学系）；Department of Computer Science, University of Pisa, Pisa, Italy（比萨大学计算机科学系）；CENTAI Institute, Turin, Italy（CENTAI研究院）
Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study
Norwegian University of Science and Technology (NTNU)（挪威科技大学）；AiBA AS（AiBA公司）；Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所IGD）；Goa University（果阿大学）
