1 Hit in 1.6 sec

pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing [article]

Jiasi Weng, Jian Weng, Gui Tang, Anjia Yang, Ming Li, Jia-Nan Liu
This paper proposes a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing, enabling a CNN model developer to convince a user of the truthful CNN performance over  ...  To balance the security and efficiency issues, three new efforts are done by appropriately integrating homomorphic encryption (HE) and zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK  ...  INTRODUCTION Convolutional neural networks (CNNs) [1] , [2] have been widely applied in various application scenarios, such as healthcare analysis, autonomous vehicle and face recognition.  ... 
doi:10.48550/arxiv.2201.09186 fatcat:nizbstndaraglhzbb6xp4c22re