SCNN: A Secure Convolutional Neural Network using Blockchain
Inzamam Mashood Nasir, Muhammad Attique Khan, Ammar Armghan, Muhammad Younus Javed
Abstract
Real-time applications like object detection, fire detection, face recognition and cancer detection are solely or partially relying on deep learning algorithms. Any tempering in these models can cause huge damages in many ways, therefore an utter need to secure these deep learning models is critically required. Blockchain technology has gained a wide popularity in tractability and security. In this article, the properties of blockchain are applied on the CNN models to produce secure CNN models. Each layer of a CNN model relates to a block, which contains the hash keys, public and private keys of their neighbors, while there exists a ledger block, which contains the detailed information about each layer of the model. The proposed SCNN model is tested using SVGG19 and SInceptionV3 models on publicly available datasets, which provides satisfactory results.