Abstract
Biometric verification systems have become prevalent in the modern world with the wide usage of smartphones. These systems heavily rely on storing the sensitive biometric data on the cloud. Due to the fact that biometric data like fingerprint and iris cannot be changed, storing them on the cloud creates vulnerability and can potentially have catastrophic consequences if these data are leaked. In the recent years, in order to preserve the privacy of the users, homomorphic encryption has been used to enable computation on the encrypted data and to eliminate the need for decryption. This work presents DeepZeroID: a privacy-preserving cloud-based and multiple-party biometric verification system that uses homomorphic encryption. Via transfer learning, training on sensitive biometric data is eliminated and one pre-trained deep neural network is used as feature extractor. By developing an exhaustive search algorithm, this feature extractor is applied on the tasks of biometric verification and liveness detection. By eliminating the need for training on and decrypting the sensitive biometric data, this system preserves privacy, requires zero knowledge of the sensitive data distribution, and is highly scalable. Our experimental results show that DeepZeroID can deliver 95.47% F1 score in the verification of combined iris and fingerprint feature vectors with zero true positives and with a 100% accuracy in liveness detection.
Highlights
Biometrics is a tool to automatically distinguish subjects in a reliable manner for a target application based on the derived signals from physical or behavioral traits
The DeepZeroID system uses only fingerprint and iris, but it can be extended to outputs of specific layers of this network are extracted as the feature vectors for the inputs
While DenseNet was trained on images of everyday objects, the patterns learnt within proved to be useful in extracting features from both iris and fingerprint images in both tasks of verification and liveness detection
Summary
Biometrics is a tool to automatically distinguish subjects in a reliable manner for a target application based on the derived signals from physical or behavioral traits (such as fingerprint, iris, palm veins, face, DNA, voice pattern, facial pattern, and hand geometry). A BRS has had applications in the law enforcement for decades in authentication of individuals; nowadays smartphones rely on biometrics for verification of the user as well These systems include server-side database owner and users who submit candidate biometric records for verification of the identity profiles. These data can be used to measure biological characteristics for identification and classification of entities. The fundamental concepts and techniques that are utilized in this work are discussed These concepts and techniques include transfer learning, homomorphic encryption, leveraged pre-trained deep neural networks (which are DenseNet and AlexNet), and the process of true/fake detection of the biometric data. Each task is learned from the scratch in these techniques
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
