| Title | Training Neural Network Over Encrypted Data |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Molek, V., Hurtik, P. |
| Conference Name | 2020 IEEE Third International Conference on Data Stream Mining Processing (DSMP) |
| Date Published | aug |
| Keywords | convolutional classifier, convolutional neural nets, convolutional neural network classifier, convolutional neural networks, cryptography, encrypted data, Encryption, Fuzzy Cryptography, image classification, Image color analysis, image data encryption, image permutation, learning (artificial intelligence), Metrics, Neural Network, pattern classification, plain data, private company policy, pubcrawl, Resiliency, Scalability, Training |
| Abstract | We are answering the question whenever systems with convolutional neural network classifier trained over plain and encrypted data keep the ordering according to accuracy. Our motivation is need for designing convolutional neural network classifiers when data in their plain form are not accessible because of private company policy or sensitive data gathered by police. We propose to use a combination of fully connected autoencoder together with a convolutional neural network classifier. The autoencoder transforms the data info form that allows the convolutional classifier to be trained. We present three experiments that show the ordering of systems over plain and encrypted data. The results show that the systems indeed keep the ordering, and thus a NN designer can select appropriate architecture over encrypted data and later let data owner train or fine-tune the system/CNN classifier on the plain data. |
| DOI | 10.1109/DSMP47368.2020.9204073 |
| Citation Key | molek_training_2020 |
Training Neural Network Over Encrypted Data