Voice Recognition for Authentication in Banking

Contactless authentication using voice recognition to improve security, convenience, and cross-platform compatibility compared to conventional authentication methods that require contact. The authentication is performed by converting an audio sample from a user device into a processed format and transmitting it to a speech recognition module. The speech recognition module compares the processed audio against user voice models to determine if it matches. If the match is successful, the user is authenticated. This allows contactless voice-based authentication that can be used on any device with a microphone and speaker, without requiring dedicated authentication devices or manual entry.

Source

Secure electronic financial transactions system that uses AI, biometrics, and multimodal data analysis to prevent fraud and improve user experience. The system collects multimodal data from visual, auditory, and tactile sensors during transactions. It uses AI modules like biometric authentication, transaction anomaly detection, geospatial analysis, behavioral analysis, and third-party data integration to analyze this data for fraud prevention. The system also communicates with users through modalities like vision, audio, touch, taste, smell, temperature, pain, and balance to address fraud concerns or request verification.

Source

Automated offline payment system that allows users to select products without manually scanning them and makes payment without using their own devices. The system uses biometric authentication to verify users and their devices. When a user selects items in a store, a dedicated terminal recognizes them. The store terminal sends biometric info to the user's device. It authenticates against stored data. If successful, the device makes payment. Leaving the store triggers payment. In product transportation units, the dedicated terminal recognizes items and requests payment. It receives biometrics from the user's device and authenticates. If successful, it pays.

Source

Secure and efficient order pickup system that uses voice authentication to verify user identity and prevent unauthorized pickups. The system associates a voice signature with each order during placement. When a user comes to pick up an order, they speak a phrase which is compared against the stored voice signature. If it matches, the user is authorized to retrieve the order. This eliminates the need for IDs or documents, improves security, and reduces errors compared to manual verification.

Source

Contact-minimized automated teller machine (ATM) using radar-based gesture recognition and authentication to eliminate the need for physical cards and keypads. The ATM has a radar transmitter to create a field in front of it. Customers interact with the ATM using gestures instead of touching buttons or cards. The radar detects the gestures and translates them into actions. The ATM can also identify customers based on unique gestures learned during account setup. This provides contactless ATM usage and reduces transmission of germs.

Source

Improving authentication security by generating and processing user responses to authentication questions in a narrative format. The responses are textual inputs like "I shopped at Joe's last week" instead of multiple choice options. The text is processed to identify merchants and compare to transaction data. A machine learning model predicts guessability based on merchant popularity. If a user correctly identifies a matched merchant, the authentication score is determined based on guessability. This provides more secure authentication by preventing guessing and profiling from predefined options.

Source

Enabling users to schedule payments using voice or text commands through a payment app, without needing to navigate complex menus or remember OTPs. The app extracts payment instructions from natural language input and authenticates the user based on factors like location, facial features, typing patterns, etc. This allows scheduling payments using conversational commands like "Pay my credit card bill on Thursday" or "Send $50 to Mom next week". The app encrypts the instruction and factors and sends to the server, which processes the scheduled payment. This provides an intuitive and convenient way to schedule payments using natural language input and automatic authentication.

Source

Using machine learning to improve user authentication in financial transactions by generating more effective challenge questions that are tailored to the specific transactions of an authorized user. The method involves training a machine learning model to identify financial transactions that an authorized user is likely to remember based on their transaction history. This allows generating challenge questions about recent transactions that are more likely to be answered correctly by the authorized user.

Source

Enhancing user authentication using a smart device like a smart speaker to improve security and reliability. The method involves using transaction-based authentication questions like "What was your credit card purchase on May 12?" instead of static questions. The user's voice is analyzed during the responses to determine if it matches an expected voiceprint. If so, fewer questions are needed for authentication. If not, more questions are required. This combines voice analysis with dynamic transaction-based questions to prevent spoofing of prerecorded voices.

Source

Exchanging data for secure transactions over voice channels to enable voice-based payment and other transactions. The method involves monitoring voice conversations for transaction requests, extracting details from the voice, confirming with the user, and carrying out the transaction using the extracted data. It uses voice encoding to embed transaction requests in audio and voice decoding to extract them. This allows performing transactions without separate channels or devices.

Source

Enhanced security for accessing resources like bank accounts using biometric verification at the time of transaction in addition to PIN entry. The method involves comparing current biometric data with historical data to ensure consistency. This prevents unauthorized use of stolen cards or compromised PINs. A generative adversarial network (GAN) is trained to enhance biometric data and generate distributions for verification. It analyzes discrepancies and determines if multiple users could match the data.

Source

Training a machine learning model for simultaneously authenticating a user and determining liveness of the user's biometric voice data. The training involves using a dataset of audio signals with user identities and flags indicating if the audio was live or synthetic. The model learns embeddings from the audio signals and optimizes losses like triplet loss to successfully verify user identity and liveness. This joint training allows the model to authenticate users and detect spoofing attacks like voice cloning or conversion.

Source

Verifying digital payments using machine learning models to determine whether an authentication is waived. The system receives service data associated with a transaction from a user's device. It uses a blacklist generated from machine learning models to automatically determine if authentication is required. If the user and transaction attributes are not on the blacklist, the system approves the payment without requesting authentication. If they are on the blacklist, it requests authentication and validates it. This balances convenience with security by avoiding unnecessary authentication requests for low-risk transactions.

Source

Securely validating credentials like bank account numbers without exposing the actual credentials. The method involves training a neural network to infer validity of encrypted credentials. The neural network is then encrypted using the same homomorphic encryption as the credentials. This allows validating encrypted credentials without decrypting them. The encrypted validity indicators can be provided back to the original source without exposing the original encrypted credentials.

Source

Authenticating users based on their behavioral biometric data like speech patterns and touch inputs to improve accuracy and prevent impersonation compared to traditional authentication methods like PINs or passwords. The technique involves generating challenge questions based on the user's recent transactions, prompting the user to respond audibly and/or via touch, extracting behavioral biometric data from the responses, and using machine learning models trained on user-specific biometric data to verify the user's identity.

Source

Authorizing transactions involving smartcards by combining smartcard usage with biometric authentication. The method involves receiving a policy message with ruleset for transaction authorization and biometric parameters. Biometric data is received and an authentication score calculated using the machine learning algorithm. The transaction is checked against the ruleset to authorize. This combines smartcard usage with biometric verification to provide improved security and reduce false positives in transaction authorization.

Source

Authenticating payment transactions using behavioral biometrics to quickly determine user identity and approve transactions without multiple authentication steps. The method involves embedding a behavioral biometrics service in merchant webpages/apps that collects transaction and user data. This data is sent to a behavioral biometrics server for analysis to generate an authentication response. If the response indicates lack of authenticity, an alert is sent to merchant, app, and issuer. This allows quicker approval without extra authentication if behavior matches known patterns. It also provides an additional layer of authentication called cloaking for PSD2 compliance.

Source

A security tool that uses a user's location history and voice biometrics to detect and prevent credit card fraud. The tool analyzes historical transactions, locations, and voice data to determine fraud probability. If a transaction looks suspicious, it requires vocal confirmation from the user. If the voice matches, the transaction is authorized. This reduces false positives compared to just transaction history. It also allows faster reactivation of frozen accounts.

Source

Secure financial transactions using augmented reality headsets for seamless and convenient payments without requiring physical cards or identification. The system uses eye tracking and neural networks to recognize users based on unique eye features. It allows users to make transactions by scanning their eyes instead of presenting cards or IDs. The neural networks analyze eye images to identify users. This provides contactless payments and eliminates the need for physical tokens or IDs. The neural networks use specialized layers to accurately and precisely identify users from eye data.

Source

Dynamic voice authentication system that matches a person's current utterance with previously recorded ones to authenticate them. It isolates words and acoustic characteristics from utterances, compares them with stored ones, and transmits an authentication message if matches. This improves over static phrase authentication as it can handle pronunciation variations and compromised phrases. The system uses statistical and acoustic analysis to extract characteristics, and allows speaker repetition of generated phrases to further improve matching.

Source