This paper deals with the problem of adding privacy to the inference pipe-line of neural networks. Following previous results in this field, they propose the use of Homomorphic Encryption (HE). The authors use a different HE scheme then previous authors did which allows them to compute ReLUs and other activations that were only approximated in previous studies. They manage to do that while preserving relatively good computation time. This is a significant contribution as it suggest an alternative approach to the approaches used before. The authors may wish to include more recent results in Table 4. Some of this paper were published after the submission deadline but other were available even before this deadline. [1] Boemer and others, “nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data” [2] Boemer and others, “nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data” [3] Brutzkus and others “Low Latency Privacy Preserving Inference”