Abstract: A system and method for verifying a signature in real-time when authenticating a card-based transaction. Initially, a digital reference signature is captured on a mobile device, sent in hashed form to a rules engine, and evaluated for features such as length, time, orientation, area, and pressure changes. Subsequently, a digital transaction signature is captured on a POS terminal, sent in hashed form to the rules engine via an acquirer, and evaluated for the same features. The rules engine compares the features of the signatures. If the transaction signature is verified, the rules engine sends an authentication token to the acquirer, and the acquirer sends the token and an authorization request to an issuer. If not, the acquirer sends a denial message to the merchant. If the power level of the POS terminal is insufficient to properly capture the transaction signature for effective evaluation, then an alternative authentication method is used.

Abstract: A system and method for reducing financial fraud by suspending access to financial accounts due to a user's incapacitation. A fall detection alert is received from a device worn or carried by the user, and first status values are recorded. After a pre-established period of time, second status values are recorded, and the first and second status values are compared. An incapacitation of the user is inferred if the second status values are within a pre-established range of the first status values, and access to the accounts is suspended for at least some purchases based on this inferred incapacitation. Prior to suspending access, a notification may be sent to the user to allow the user to act to avoid the suspension. Access to the accounts may not be suspended for medical or other relevant purchases. Subsequent to suspending access, the user may request and access may be reinstated.

Abstract: Registering a biometric template with a computing device includes receiving a first scan of a biometric feature from a biometric sensor. The first scan includes first biometric data. The computing device extracts two or more distinct elements of the biometric feature and writes a biometric template to a memory. The first characterization data for each of the two or more distinct elements is recorded in the biometric template. After recording the first characterization data in the biometric template, the computing device receives an additional scan of the biometric feature from the biometric sensor. The additional scan includes second biometric data. The computing device validates the biometric template against the second biometric data. After validating the biometric template, the biometric template is updated with second characterization data. The second characterization data is associated with two or more additional distinct elements of the biometric feature contained in the second biometric data.

Abstract: A method for authentication of non-fungible tokens (NFTs) includes receiving a validation request for an NFT from an external platform including a smart contract identifier; calculating an authentication score for the NFT based on at least (i) wallet activity associated with a creator blockchain wallet identified based on the smart contract identifier, and (ii) a fraud score of the external platform; and if the calculated authentication score for the NFT is below a predetermined threshold value, transmitting a negative response message to the validation request indicating unsuccessful validation of the NFT, or if the calculated authentication score for the NFT is above the predetermined threshold value, transmitting a positive response message to the validation request indicating successful validation of the NFT and instructing the external platform to execute a smart contract associated with the smart contract identifier.

Abstract: A system and method for performing a transaction at a software-based POS system of a merchant includes receiving, from the software-based POS system, a payment authorization request message. A processor is programmed to extract a dynamic hashed security token from the payment authorization request message. In addition, the processor is programmed to validate the dynamic hashed security token and, upon validating the dynamic hashed security token, determine that the software-based POS system that transmitted the payment authorization request message is running a mobile POS software application. Furthermore, the processor is programed to extract the hardware identifier and the application identifier from the transaction data and compare them to account registration information stored with a merchant account.

Abstract: Registering a biometric template with a computing device includes receiving a first scan of a biometric feature from a biometric sensor. The first scan includes first biometric data. The computing device extracts two or more distinct elements of the biometric feature and writes a biometric template to a memory. The first characterization data for each of the two or more distinct elements is recorded in the biometric template. After recording the first characterization data in the biometric template, the computing device receives an additional scan of the biometric feature from the biometric sensor. The additional scan includes second biometric data. The computing device validates the biometric template against the second biometric data. After validating the biometric template, the biometric template is updated with second characterization data. The second characterization data is associated with two or more additional distinct elements of the biometric feature contained in the second biometric data.

Abstract: The disclosure describes techniques for authenticating a voice command transaction initiated by a consumer at a voice-activated digital assistant. The system determine a proximity score for a consumer device. The proximity score is based on a distance between the consumer device and the digital assistant. The system detects motion indicating presence of a person proximate the digital assistant (based on wireless signal data) and determines a motion score. The system receives voice data from the digital assistant and determines a voice differentiation score. The system determines a rank score for the consumer device based on historical transaction data associated with the device. The system analyzes the proximity score, motion score, voice differentiation score, and rank score using a voice command authentication model. Based on the analysis, the system determines an authentication score for the voice command transaction request.

Abstract: The disclosure describes systems and techniques for assessing risk of an open Wi-Fi network, at a consumer's request, before the consumer performs a transaction. The system receives a Wi-Fi network risk assessment request associated with a Wi-Fi network connection of a mobile device. Upon receiving the request, the system retrieves connection-related data from the mobile device. The connection-related data is associated with the Wi-Fi network connection. The system performs a Wi-Fi risk assessment of the Wi-Fi network connection. The system transmits a result of the risk assessment to the mobile device for presentation on the mobile device. The system also transmits the result of the risk assessment to an issuer server. The issuer server is associated with a payment account of the consumer. Moreover, the system transmits a step-up authentication alert to the issuer server.

Abstract: An audio file authentication system configured to extract a plurality of audio features for a plurality of raw audio files containing a digital recording of a specific user's voice, provide an authenticated audio file that includes a digital recording the specific user's voice based on the authentication information for the specific user, generate a parent hash key and sequential child hash keys that are unique to the authenticated audio file, and generate a processed audio file in which the parent hash key and each of the sequential child hash keys is inserted sequentially as data within the audio gaps of the audio file.

Abstract: The disclosure describes systems and techniques for assessing risk of an open Wi-Fi network, at a consumer's request, before the consumer performs a transaction. The system receives a Wi-Fi network risk assessment request associated with a Wi-Fi network connection of a mobile device. Upon receiving the request, the system retrieves connection-related data from the mobile device. The connection-related data is associated with the Wi-Fi network connection. The system performs a Wi-Fi risk assessment of the Wi-Fi network connection. The system transmits a result of the risk assessment to the mobile device for presentation on the mobile device. The system also transmits the result of the risk assessment to an issuer server. The issuer server is associated with a payment account of the consumer. Moreover, the system transmits a step-up authentication alert to the issuer server.

Abstract: A device and method of authentication includes pairing a card to a mobile electronic device and a wearable device. A machine learning model is trained by obtaining first received signal strength indicator (RSSI) data from the card, the mobile electronic device, and the wearable device at calibrated distances. A first estimated proximity radius encompassing the card, the mobile electronic device, and the wearable device is calculated. The first estimated proximity radius is classified to be within a threshold. Upon receipt of a request to authorize a request, second RSSI data from the card, the mobile electronic device, and the wearable device is obtained. A second estimated proximity radius encompassing the card, the mobile electronic device, and the wearable device is calculated. Using the trained machine learning model, the second estimated proximity radius is determined to be within the threshold. Authentication is then complete.

Abstract: A computer system includes a processor programmed to process a first web page to identify a hyperlink contained thereon. The hyperlink includes a link to a second web page. The processor performs natural language processing on the first web page to determine one or more context word tokens and on the second web page to determine a context of the second web page. The processor also applies a context relevant tag to the hyperlink to generate a tagged hyperlink. The processor maps at least one of the context word tokens to the context relevant tag applied to the hyperlink and generates a transaction score for the tagged hyperlink.

Abstract: A computer system includes a processor programmed to process a first web page to identify a hyperlink contained thereon. The hyperlink includes a link to a second web page. The processor performs natural language processing on the first web page to determine one or more context word tokens and on the second web page to determine a context of the second web page. The processor also applies a context relevant tag to the hyperlink to generate a tagged hyperlink. The processor maps at least one of the context word tokens to the context relevant tag applied to the hyperlink and generates a transaction score for the tagged hyperlink.

Abstract: The disclosure describes systems and techniques for assessing risk of an open Wi-Fi network, at a consumer's request, before the consumer performs a transaction. The system receives a Wi-Fi network risk assessment request associated with a Wi-Fi network connection of a mobile device. Upon receiving the request, the system retrieves connection-related data from the mobile device. The connection-related data is associated with the Wi-Fi network connection. The system performs a Wi-Fi risk assessment of the Wi-Fi network connection. The system transmits a result of the risk assessment to the mobile device for presentation on the mobile device. The system also transmits the result of the risk assessment to an issuer server. The issuer server is associated with a payment account of the consumer. Moreover, the system transmits a step-up authentication alert to the issuer server.

Abstract: The disclosure describes techniques for authenticating a voice command transaction initiated by a consumer at a voice-activated digital assistant. The system determine a proximity score for a consumer device. The proximity score is based on a distance between the consumer device and the digital assistant. The system detects motion indicating presence of a person proximate the digital assistant (based on wireless signal data) and determines a motion score. The system receives voice data from the digital assistant and determines a voice differentiation score. The system determines a rank score for the consumer device based on historical transaction data associated with the device. The system analyzes the proximity score, motion score, voice differentiation score, and rank score using a voice command authentication model. Based on the analysis, the system determines an authentication score for the voice command transaction request.

Abstract: Systems and methods are provided for determining if an e-mail originating from an external source is deemed malicious and thereby preventing an out of office e-mail reply. One example method includes receiving, at a computing device of a service provider, an e-mail identified as originating from an external source, scanning the e-mail to identify at least one parameter only when an out of office reply is setup by a recipient of the e-mail, comparing the at least one scanned parameter to a set of known parameters, calculating a score of the e-mail based on the comparison of the at least one parameter to a set of known parameters, determining the e-mail to be a malicious e-mail if the score exceeds a threshold value and blocking an out of office reply based on the threshold value.

Abstract: A computer system includes a processor programmed to process a first web page to identify a hyperlink contained thereon. The hyperlink includes a link to a second web page. The processor performs natural language processing on the first web page to determine one or more context word tokens and on the second web page to determine a context of the second web page. The processor also applies a context relevant tag to the hyperlink to generate a tagged hyperlink. The processor maps at least one of the context word tokens to the context relevant tag applied to the hyperlink and generates a transaction score for the tagged hyperlink.