Systems and methods for generating and applying a secure statistical classifier

A system for protecting against malicious manipulation of input using a secure statistical classifier, comprising:

• at least one hardware processor executing a code for:
• receiving input for classification by a secure statistical classifier, wherein the secure statistical classifier includes a plurality of trained sub-classifiers;
• providing the input to each of the plurality of trained sub-classifiers, wherein each of the plurality of trained sub-classifiers includes a respective instance of an untrained statistical classifier trained on a sub-training dataset of a plurality of sub-training datasets, each sub-training dataset including a plurality of records, each record including a combined input data item generated from a combination of a training input data item of a main training dataset and at least one unique cryptographic key of a plurality of cryptographic keys, and a ground truth label of the training input data item included in the combined input data item, by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to the combined input data item of the sub-training dataset serving as input generated from the combination of the training input data item and the at least one unique cryptographic key and a corresponding ground truth label,
• wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to the corresponding at least one unique cryptographic key of the sub-training dataset;
• computing in response to a plurality of classification outputs from the plurality of trained sub-classifiers at least one of a single classification output and an indication of likelihood of malicious manipulation;
• and
• causing execution of code instructions by a controller such that the controller controls at least one of:
• an automated driving vehicle, and a semi-automated driving vehicle, said code instructions are generated according to at least one of the single classification output and the indication of likelihood of malicious manipulation of input;
• wherein each of the respective instances of the untrained statistical classifier is trained using a different cryptographic key.

A method of protecting against malicious manipulation of input using a secure statistical classifier, the method comprising:

• by at least one hardware processor executing a code for:
• receiving input for classification by a secure statistical classifier, wherein the secure statistical classifier includes a plurality of trained sub-classifiers;
• providing the input to each of the plurality of trained sub-classifiers, wherein each of the plurality of trained sub-classifiers includes a respective instance of an untrained statistical classifier trained on a sub-training dataset of a plurality of sub-training datasets, each sub-training dataset including a plurality of records, each record including a combined input data item generated from a combination of a training input data item of a main training dataset and at least one unique cryptographic key of a plurality of cryptographic keys, and a ground truth label of the training input data item included in the combined input data item, by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to the combined input data item of the sub-training dataset serving as input generated from the combination of the training input data item and the at least one unique cryptographic key and a corresponding ground truth label,
• wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to the corresponding at least one unique cryptographic key of the sub-training dataset;
• computing in response to the plurality of classification outputs from the plurality of trained sub-classifiers at least one of a single classification output and an indication of likelihood of malicious manipulation;
• and
• causing execution of code instructions by a controller such that the controller controls at least one of:
• an automated driving vehicle, and a semi-automated driving vehicle wherein said code instructions are generated according to at least one of the single classification output and the indication of likelihood of malicious manipulation of input;
• wherein each of the respective instances of the untrained statistical classifier is trained using a different cryptographic key.