Bank of America Corporation

Kelly Renee-Drop Keiter

Cody Dean Searl

Christopher Daniel Birch

Susan R Hart

Lisa Matthews

Michael Robert Young

Tomas Mata Castrejon, Iii

Kyle A Mayers

Sanjay Arjun Lohar

Rick Wayne Sumrall

Richard Martin Seymour Scot

Richard Scot

Robert Nyeland Huggins

Michael Young

Graham Wyllie

W Scott Hammet

James R Crocker

Apparatus and methods for using deepfakes defensively to detect fake, spoofed, and hoax phone calls and videoconferences are provided. A program may record a target individual reciting exemplary phrases. The program may analyze the recordings to create a baseline. The program may use deepfake algorithms to create exemplar deepfake audiovisual representations of the target individual. The program may store the data in a database. The program may analyze, in real-time, a phone call or videoconference to determine whether they are legitimate or illegitimate by comparing the audio or audiovisual contents of the phone call or videoconference with the exemplar deepfakes. When the program determines the phone call or videoconference is illegitimate, the program may terminate the call or videoconference and inform the recipient and others.

Defensive deepfake for detecting live deepfaked audio and video

Arrangements for providing frictionless unauthorized activity detection and user authentication are provided. In some aspects, user data, such as transaction data may be received and used to train a machine learning model. In some examples, the machine learning model may be executed to generate one or more expected user patterns. In some arrangements, a request for transaction may be received. The request for transaction may include transaction details. In response, the system may request current geo-location data of a user. In some examples, the transaction details and geo-location data may be analyzed (e.g., compared to the expected user patterns) to generate an authentication output. The authentication output may then be transmitted to one or more systems to process the requested transaction, prevent transaction processing, or the like.

Secure user authentication using machine learning and geo-location data

A system for communicating email messages using tokens receives a request to send an email message to a receiver. The email message is associated with a sender's email address. The system determines whether the sender's email address is associated with a token from a plurality of tokens stored in a token-email address mapping table. The system generates a particular token for the sender's email address in response to determining that the sender's email address is not associated with a token, where the particular token uniquely identifies the sender's email address. The system sends the email message using the particular token instead of the sender's email address, such that the sender's email address remains anonymous from the perspective of the receiver.

Information security system and method for phishing threat prevention using tokens

Apparatus and methods for using deepfakes defensively to detect fake, spoofed, and hoax accounts and posts on social media and elsewhere are provided. A program may gather verified images or writings of a target individual. The program may analyze the verified images and writings to create a baseline. The program may use deepfake algorithms to create exemplar deepfake images or writings. The program may store the data in a database. The program may search a network for social media accounts or posts that may meet the baseline and determine whether they are legitimate or illegitimate by comparing the contents of the accounts or posts with the exemplar deepfakes. When the program determines the accounts or posts are illegitimate, the program may initiate a takedown of those accounts or posts. The program may use machine learning algorithms to refine itself and become more accurate.

Defensive deepfake for detecting spoofed accounts

A system for phishing domain detection receives a communication associated with a particular domain. The system extracts a first set of features from the communication, the first set of features including a name of the sender, a name of the domain, a time of receipt, a sentiment message, and attachment file associated with the communication. The system compares the first set of features with a second set of features associated with a historical communication labeled with a phishing domain. In response to determining that the first set of features corresponds to the second set of features, the system determines that the particular domain is the phishing domain.

Information security system and method for phishing domain detection

A system for preventing communications from detected phishing domains receives a communication associated with a particular domain. The system determines that the particular domain is a phishing domain. In response, in one embodiment, the system registers the particular domain in a Domain Name System (DNS) server to block the communication and future communications associated with the particular domain from being received at computing devices operably coupled with the DNS server. In another embodiment, the system registers the particular domain in the DNS server, such that the communication and future communications associated with the particular domain are re-routed to a particular server to monitor phishing activities implemented on the communications, where the phishing activities comprise attempting to obtain login credentials and private information associated with receivers of the communication and future communications.

Information security system and method for preventing communications from detected phishing domains

A system for identifying email messages associated with phishing threats accesses an email message sent to a receiving computing device, where the email message is associated with a sender's email address. The system determines whether the sender's email address is associated with a token from a plurality of tokens stored in a token-email address mapping table. The system determines that the email message is associated with a phishing threat, in response to determining that the sender's email address is not associated with a token from a plurality of tokens from among a token-email mapping table.

Information security system and method for phishing threat detection using tokens

Embodiments of the present invention provide a system for providing selective security regulations associated with network communications to users. The system is configured for extracting user data associated with a user, identifying one or more characteristics based on the extracted user data, generating a custom security package for the user based on the one or more characteristics, displaying one or more options associated with the custom security package on a user device of the user, prompting the user to select at least one option from the one or more options, receiving the at least one option from the user, and deploying a functionality associated with the at least one option from the custom security package.

Selective security regulation for network communication

Embodiments of the present invention provide systems and methods for evaluating and weighting resource usage activity data. The system may establish a communicable link to a user device via a user application to receive resource activity data and historical data from one or more users or systems via multiple communication channels. The system may evaluate the historical data and determine evaluation criteria based on perceived chance of loss associated with particular metadata characteristics, and use the evaluation criteria as weighted metrics for determining an overall evaluation score for the user based on indication from resource activity data that the user has conducted resource transfers with entities or channels identified in the historical data.

System for evaluation and weighting of resource usage activity

Embodiments of the present invention provide systems and methods for generation and maintenance of verified data records. The system may receive a data submission from a user device over one or more communication channels and convert the data submission into a normalized text format for processing and analysis. The data submission may then be analyzed using one or more trained machined learning models in order to identify factual statements and modifiers within the data submission, and generate a confidence score of verified factual information based on corroboration with one or more additional data sources. Additionally, identified modifiers may be analyzed to determine positive or negative sentiment.

System for generation and maintenance of verified data records

Verification of the identities of parties participating in network-based communication, such as telephone communication, including SMS/text communication, email communication and the like is provided. Communication identifiers (IDs) (e.g., telephone numbers, email addresses or the like) are verified as being associated with one or more communication parties and, in response, a verified communication (ID) database is established. The verified communication ID database is relied upon when a user/communication is selecting a communication ID as an address for an impending communication or receiving a communication for determining whether the communication ID is verifiably associated with a known communication party. If the communication ID is determined to be verifiably associated with a known communication party, a visual or audible output may be provided on the user's device or within the communication that indicates that the communication ID is verifiably associated with the known communication party.

Systems for verifying identities of parties participating in distributed network communication

A system for secure data transfer is provided. The system is configured to: generate a database of verified interaction providers comprising verified provider information; determine that a user device has accessed a data transfer location associated with an interaction provider; install a proxy server over the data transfer location, wherein data transfer traffic between the user device and the interaction provider is routed through and monitored by the proxy server; determine, via the proxy server, that the user device has requested an interaction at the data transfer location, the interaction comprising a data transfer; determine that the interaction provider associated with the data transfer location is in the database of verified interaction providers; and in response to determining that the interaction provider is in the database, complete the data transfer through the proxy server.

Growing community of inventors

Waxhaw, NC, United States of America

Kelly Renee-Drop Keiter