Encoding and reconstructing inputs using neural networks

A system comprising:

• one or more processors;
• and
• one or more computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
• obtaining a plurality of training data pairs for a neural network system, each training data pair comprising a respective first input and a respective second input;
• and
• training the neural network system on the plurality of training data pairs, comprising, for each training data pair:
• processing, using an encoder neural network in accordance with current values of parameters of the encoder neural network, (i) the respective first input for the training data pair and (ii) the respective second input for the training data pair to generate an encoded representation of the respective first input for the training data pair, wherein the respective second input for the training data pair represents a private key of a public-private key pair;
• processing, using a first decoder neural network in accordance with current values of parameters of the first decoder neural network, (i) the encoded representation of the respective first input for the training data pair and (ii) the respective second input for the training data pair or a respective third input for the training data pair to generate a first estimated reconstruction of the respective first input for the training data pair, wherein the respective third input for the training data pair represents a public key of the public-private key pair, wherein (i) the respective second input for the training data pair is derived from the respective third input for the training data pair, (ii) the respective third input for the training data pair is derived from the respective second input for the training data pair, or (iii) the respective second input for the training data pair and the respective third input for the training data pair are both derived using a common procedure so as to be complementary to each other;
• obtaining a second estimated reconstruction of the respective first input for the training data pair, the second estimated reconstruction generated by a second decoder neural network in accordance with current parameters of the second decoder neural network, by processing the encoded representation of the respective first input for the training data pair without processing the respective second input for the training data pair;
• and
• adjusting the current parameters of the encoder neural network and the current parameters of the first decoder neural network based on the respective first input, the first estimated reconstruction of the respective first input, and the second estimated reconstruction of the respective first input.

One or more non-transitory computer-readable media having instructions stored thereon that, when executed by one or more processors, cause performance of operations comprising:

• obtaining a plurality of training data pairs for a neural network system, each training data pair comprising a respective first input and a respective second input;
• and
• training the neural network system on the plurality of training data pairs, comprising, for each training data pair:
• processing, using an encoder neural network in accordance with current values of parameters of the encoder neural network, (i) the respective first input for the training data pair and (ii) the respective second input for the training data pair to generate an encoded representation of the respective first input for the training data pair, wherein the respective second input for the training data pair represents a private key of a public-private key pair;
• processing, using a first decoder neural network in accordance with current values of parameters of the first decoder neural network, (i) the encoded representation of the respective first input for the training data pair and (ii) the respective second input for the training data pair or a respective third input for the training data pair to generate a first estimated reconstruction of the respective first input for the training data pair, wherein the respective third input for the training data pair represents a public key of the public-private key pair, wherein (i) the respective second input for the training data pair is derived from the respective third input for the training data pair, (ii) the respective third input for the training data pair is derived from the respective second input for the training data pair, or (iii) the respective second input for the training data pair and the respective third input for the training data pair are both derived using a common procedure so as to be complementary to each other;
• obtaining a second estimated reconstruction of the respective first input for the training data pair, the second estimated reconstruction generated by a second decoder neural network in accordance with current parameters of the second decoder neural network, by processing the encoded representation of the respective first input for the training data pair without processing the respective second input for the training data pair;
• and
• adjusting the current parameters of the encoder neural network and the current parameters of the first decoder neural network based on the respective first input, the first estimated reconstruction of the respective first input, and the second estimated reconstruction of the respective first input.