Systems and processes for lossy biometric representations

A system comprising:

• at least one processor;
• and
• a non-transitory, machine-readable memory device comprising instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to:
• obtain a biometric representation of a subject, wherein the biometric representation was encoded from a biometric sample via a neural network;
• project the biometric representation based on one or more lossy transformation parameters to generate an anonymized vector representation;
• receive a second biometric representation associated with the subject;
• generate a second anonymized vector representation based on the second biometric representation;
• and
• perform a comparison between the anonymized vector representation and the second anonymized vector representation to determine if the second anonymized vector representation is within a similarity threshold of the anonymized vector representation.

A non-transitory, computer-readable medium comprising instructions that, when executed by a computer, cause the computer to:

• obtain a biometric representation of a subject, wherein the biometric representation was encoded from a biometric sample via a neural network;
• project the biometric representation based on one or more lossy transformation parameters to generate an anonymized vector representation;
• receive a second biometric representation associated with the subject;
• generate a second anonymized vector representation based on the second biometric representation;
• and
• perform a comparison between the anonymized vector representation and the second anonymized vector representation to determine if the second anonymized vector representation is within a similarity threshold of the anonymized vector representation.