Methods and systems for enhancing detection of fraudulent authentication data

An electronic device for enhancing security during a biometric authentication transaction comprising:

• a processor;
• and
• a memory configured to store data, said electronic device being associated with a network and said memory being in communication with said processor and having instructions stored thereon which, when read and executed by said processor, cause said electronic device to:
• compute a feature vector from biometric modality data of a person and normalize the feature vector, the feature vector includes components;
• generate, for the authentication transaction, a perturbation vector;
• select components of the normalized feature vector for modification;
• modify the selected components using the perturbation vector to generate a modified feature vector;
• normalize the modified feature vector;
• encode the normalized modified feature vector into qubits;
• expand, using a quantum algorithm, the qubits into a high-dimensional space;
• detect in the high-dimensional space anomalies indicative of fraud;
• calculate, based on the detected anomalies, an anomaly score, a replay-separation score, and a confidence score, the anomaly and confidence scores reflecting the likelihood that the biometric modality data is genuine and the replay-separation score being based on authentication states;
• compare the anomaly, replay-separation, and confidence scores against respective threshold values;
• and
• when at least one of the anomaly, the replay-separation, and confidence scores fails to satisfy the respective threshold value, determine the biometric modality data requires secondary authentication.

A non-transitory computer-readable recording medium in an electronic device for enhancing security during a biometric authentication transaction, the non-transitory computer-readable recording medium storing instructions which when executed by a hardware processor cause the non-transitory recording medium to perform steps comprising:

• computing a feature vector from biometric modality data of a person and normalizing the feature vector, the feature vector includes components;
• generating, for the authentication transaction, a perturbation vector;
• selecting components of the normalized feature vector to be modified;
• modifying the selected components using the perturbation vector to generate a modified feature vector;
• normalizing the modified feature vector;
• encoding the normalized modified feature vector into qubits;
• expanding, using a quantum algorithm, the qubits into a high-dimensional space;
• detecting in the high-dimensional space anomalies indicative of fraud;
• calculating, based on the detected anomalies, an anomaly score, a replay-separation score, and a confidence score, the anomaly and confidence scores reflecting the likelihood that the biometric modality data is genuine and the replay-separation score being based on authentication states;
• comparing the anomaly, replay-separation, and confidence scores against respective threshold values;
• and
• when at least one of the anomaly, replay-separation, and confidence scores fails to satisfy the respective threshold value, determining the biometric modality data requires secondary authentication.