Reviews: SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

The authors introduce a new neural network model which enables a client to verify that its request to execute inference over a neural network has been done correctly by a server. SafetyNets provide the client a high-probability guarantee of detecting wrong/lazy executions by the server, and incurs only a low overhead for the server while significantly decreasing the client's computation compared to executing the network itself. SafetyNets come with severe restrictions on the network during inference, but experimentally these restrictions are shown to have little impact on network performance. Quality: The experiments are convincing; the theory is an extension to the specific setting of neural networks of related work on interactive proofs. Clarity: This paper is very clear and easy to understand.