Systems and methods for dividing filters in neural networks for private data computations

A system for maintaining security of a convolutional neural network, the system comprising:

• a processor;
• a convolutional neural network operating via the processor;
• and
• a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising:
• dividing a plurality of filters in a first layer of the convolutional neural network into a first set of filters and a second set of filters;
• applying, via the convolutional neural network, each of the first set of filters to an input of the convolutional neural network to yield a first set of outputs;
• obtaining a second set of outputs associated with the second set of filters;
• for each set of filters in the first set of filters and the second set of filters that corresponds to a same filter from the plurality of filters, aggregating a respective one of the first set of outputs with a respective one of the second set of outputs to yield a set of aggregated outputs;
• splitting respective weights of specific neurons activated in each remaining layer of the convolutional neural network to yield a first set of weights and a second set of weights, wherein at least one remaining layer in the convolutional neural network comprises at least one of a pooling layer, a normalization layer, a fully-connected layer, and an output layer;
• sending the second set of weights to a remote computing device separate from the system;
• at each specific neuron from each remaining layer, applying a respective filter associated with each specific neuron and a first corresponding weight from the first set of weights to yield a first set of neuron outputs;
• obtaining, from the remote computing device, a second set of neuron outputs associated with the specific neurons, the second set of neuron outputs being based on an application of the respective filter associated with each specific neuron to a second corresponding weight from the second set of weights;
• for each specific neuron, aggregating one of the first set of neuron outputs associated with the specific neuron with one of the second set of neuron outputs to yield aggregated neuron outputs;
• and
• generating an output of the convolutional neural network based on one or more of the aggregated neuron outputs, wherein the operations maintain the security of the convolutional neural network and prevent the remote computing device from learning any data about the convolutional neural network.