Privacy-preserving Biometrics based Authentication and Security

基于密码的身份验证系统无法验证真正的用户。生物识别身份验证可以解决这个问题。然而，蓬勃发展的物联网应用和云计算要求生物识别认证必须在隐私保护设置中进行，以符合隐私保护法律规定。最新的报告表明，目前的生物识别认证系统，在保护设置下，表现出较差的认证性能，不适合商业应用。该项目旨在研究解决这一问题的创新方案。预计交付的成果将包括基于深度学习的生物特征提取器、可取消的生物特征和面向云的生物特征安全协议。

Password based authentication systems cannot verify genuine users. Biometric authentication can address this issue. However, the booming IoT applications and cloud computing require that the biometric authentication must be conducted in the privacy-protected setting in order to comply with privacy protection legal regulations. Latest reports show that current biometric authentication systems, under protected setting, exhibit poor authentication performance, which is not commercially applicable. This project aims to investigate innovative solutions to this issue. The intended deliverables will include deep learning based biometric feature extractor, cancellable biometrics and cloud oriented biometrics security protocols.