Bank of America Corporation

Shahadat Hossain Mazumder

Abhijit Behera

Maneesh Kumar Sethia

Sivashalini Sivajothi

A computing platform may generate, using a generative AI model, voice based authentication prompts corresponding to a user. Upon receiving a registration request from the user, the computing platform may identify the voice based authentication prompts for the user. The computing platform may send, to a first computing device of the user, the voice based authentication prompts and may receive/store voice based authentication information corresponding to the voice based audio inputs. Based on receiving an access request, the computing platform may send the plurality of voice based authentication prompts, and may receive, from a second computing device, additional voice based audio inputs. The computing platform may score, based on the voice based authentication information, the additional voice based audio inputs. The computing platform may compare the score to a threshold. Based on identifying that the score fails to meet the threshold, the computing platform may initiate security actions.

Deep fake attack prevention for voice based authentication leveraging generative artificial intelligence (AI) and distributed ledger technology

A device, during a first interaction in real time, accesses from optical cells a measurement of optical emissions generated by hardware components inside the device responsive to a data card interacting with the device, generates a first optical emission pattern based on the measurement, determines whether the first optical emission pattern matches a baseline optical emission pattern, upon determining a match, determines whether the data card is associated with prohibited interactions, upon determining the first data card is not associated with prohibited transactions, determines whether the device is connected to a malicious IP address, upon determining the device is not connected to a malicious IP address, approves the first interaction. The device declines the first interaction if the first optical emission pattern does not match the baseline optical emission pattern, the first data card is associated with prohibited interactions, or the device is connected to a malicious IP address.

System and method for improving device security based on optical absorption spectroscopy and artificial intelligence

The disclosure provides a method that includes presenting a simulated user device in a virtual environment, and receiving user credentials in response to an avatar interacting with the simulated user device. The method includes comparing the user credentials to known user credentials. The method includes determining that the avatar is associated with the user based on the comparison. The method includes identifying a first prior interaction from a data log of interactions, where the first prior interaction is associated with a first digital item token, and identifying a second prior interaction from the data log of interactions, where the second prior interaction is associated with a second digital item token. The method includes retrieving the first digital item token and the second digital item token, and presenting the first digital item token and the second digital item token on the simulated user device.

System and method for validating a digital item token on a simulated user device

A computing chip may comprise a memory that stores a machine-learning model. an optical absorption spectroscopy component, and one or more processors operably coupled to the memory and the optical absorption spectroscopy component. The one or more processors may cause the optical absorption spectroscopy component to emit radiation to N pre-determined directions within an internal space of a computing device. The one or more processors may cause the optical absorption spectroscopy component to sample an absorption of reflections of the emitted radiation for each of the N pre-determined directions. The one or more processors may determine that one or more hardware components of the computing device are in particular abnormal conditions by processing the N sampled absorptions with the machine-learning model. The one or more processors may send a notification indicating that the one or more hardware components are in the particular abnormal conditions.

Growing community of inventors

Charlotte, NC, United States of America

Shahadat Hossain Mazumder