VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Service

Machine Learning as a Service (MLaaS) allows clients with limited resources to outsource their expensive ML tasks topowerful servers. Despite the huge benefits, current MLaaS solutions still lack strong assurances on: 1) service correctness (i.e.,whether the MLaaS works as expected); 2) trustworthy accounting (i.e., whether the bill for the MLaaS resource consumption iscorrectly accounted); 3) fair payment (i.e., whether a client gets the entire MLaaS result before making the payment). Without theseassurances, unfaithful service providers can return improperly-executed ML task results or partially-trained ML models while asking forover-claimed rewards. Moreover, it is hard to argue for wide adoption of MLaaS to both the client and the service provider, especially inthe open market without a trusted third party.In this paper, we present VeriML, a novel and efficient framework to bring integrity assurances and fair payments to MLaaS. WithVeriML, clients can be assured that ML tasks are correctly executed on an untrusted server , and the resource consumption claimed bythe service provider equals to the actual workload. We strategically use succinct non-interactive arguments of knowledge (SNARK) onrandomly-selected iterations during the ML training phase for efficiency with tunable probabilistic assurance. We also develop multipleML-specific optimizations to the arithmetic circuit required by SNARK. Our system implements six common algorithms: linearregression, logistic regression, neural network, support vector machine, K-means and decision tree. The experimental results havevalidated the practical performance of VeriML.