Bank of America Corporation

Michael James Sbandi

Michael Robert Young

Jo-Ann Taylor

Sanjay Arjun Lohar

Benjamin F Tweel

Robert Cain Durbin, Jr

Adam Kristian King

Andrew Thomas Boyd

Daniel Mercado

Chiamaka Azih

Casey L Flaherty

Zarna Arun Patel

Anna Kristen Pingel Berry

Stuart David Ford

Son Huynh

Rebbecca Danielle Nelson

Marisa Kamer

Joshua Nathanael Jenkins

Angelica Barrera

Margaret M Brewer

Anna E Ganse

Vicky Kivuti

A system includes a plurality of sensors distributed about a space. Each sensor generates sensor data associated with properties of one or more people in the space. A gateway device receives the sensor data from each of the plurality of sensors and provides the sensor data to an automated response subsystem over a network. The automated response subsystem receives the sensor data. A first feature value is determined based on the received sensor data. An event score is determined based on the first feature value. The event score is compared to predefined response criteria. Based on the comparison of the event score to the predefined response criteria, an actionable event is detected, and an automated response to initiate for the detected actionable event is identified. One or both of an alert and instructions are provided in order to initiate the automated response.

System for detecting unauthorized activity

Information technology/cyber security for computer-related processes in which vulnerabilities are identified and, those vulnerabilities which are technology-related are automatically remediated by determining and executing network-based tasks. The most granular level of computer-related process assessment in made possible by reliance on a critical function/process taxonomy this is automatically generated and, as such, the present invention, identifies both technology and non-technology-related vulnerabilities.

Information technology security assessment model for process flows and associated automated remediation

A system includes a plurality of sensors distributed about a space. Each sensor generates sensor data associated with properties of one or more people in the space. An automated response subsystem receives the sensor data. An unauthorized activity performed by a first person in the space is detected based on at least a portion of the received sensor data. In response to detecting the unauthorized activity, tracking instructions are transmitted that identify the first person associated with the unauthorized activity. A tracking device receives the tracking instructions. A device associated with the first person is detected. Over a period of time, the tracking device sends queries to the device and receives corresponding responses from the device. The tracking device determines positions of the device within the space over the period of time.

System for detecting and tracking an unauthorized person

Embodiments of the invention are directed to a system, method, or computer program product for integration with a wearable device for impetus resource distribution process confirmation and authentication. In this way, the invention coordinates with a wearable device and resource distribution vehicles of a user. Upon activation of a resource distribution vehicle, the system reviews metrics from the wearable device to identify discrepancies between the real-time metrics and a baseline for the user. The invention triggers tiered confirmation requests for authentication prior to allowing processing of the resource distribution for impetus distribution prevention.

System for impetus resource distribution process confirmation with wearable device integration

Apparatus and methods for establishing a user Internet of Things ('IoT') system is provided. The method may be performed by a central IoT hub run on a user's personal computing device. The method may include detecting user devices in electronic communication with the central IoT hub and onboarding, to the user IoT system, user devices determined to be in conformance with baseline security protocols and performance characteristics. The onboarded user device may be IoT nodes. The method may include monitoring enterprise data to pre-emptively identify and address probable failures of the IoT nodes prior to failure of the IoT nodes. The method may also include addressing known failures for each IoT node on the user IoT system.

Enterprise IOT system for onboarding and maintaining peripheral devices

A plurality of communicatively coupled, networked assets may be threatened or attacked by a cybersecurity attack. The operational resiliency of the computer network determines whether the cybersecurity attack leads to a shutdown of one or more assets, or even the entire computer network. Machines and processes are disclosed to improve operational cybersecurity resiliency of software on the computer network. Machine learning is used to identify potential vulnerabilities from a vulnerability database. Chaos stress testing using a machine learning algorithm can be performed on software to exploit the vulnerabilities. A blast radius can be set to minimize any potential negative side effects of the testing. Software can be remediated to account for responses to the testing by reconfiguring to prevent exploitation of the vulnerabilities. A financial impact of the exploited vulnerabilities can be calculated and reports can be generated.

Cyber resilience chaos stress testing

A device is configured to establish a network connection with a virtual reality device and to identify a user account that is associated with the virtual reality device. The device is further configured to send a virtual simulation survey to the virtual reality device. The virtual simulation survey includes a list of virtual simulations that can be rendered by the virtual reality device. The device is further configured to receive a survey response from the virtual reality device. The survey response identifies one or more virtual simulations from the list of virtual simulations. The device is further configured to determine a cumulative user preference settings value based on the virtual simulations identified in the survey response and to modify user preference settings within the user account based on the cumulative user preference settings value.

Adjustable user preference settings using a virtual reality device

An information security system that includes an information security engine configured to detect an attack by a malicious software element in a network. The information security engine is further configured to transfer the malicious software element from the network to the emulated network in response to detecting an attack. The information security engine is further configured to select defense strategies for restricting communications using different port configurations and to implement each defense strategy within the emulated network. The information security engine is further configured to execute a duplicate of the malicious software element in the emulated network and to determine a performance level for each of the defense strategies against the duplicate of the malicious software element. The information security engine is further configured to select a defense strategy with a highest performance level and to implement the selected defense strategy within the network.

Network threat prevention and information security using machine learning

A plurality of communicatively coupled, networked assets of an organization may be threatened or attacked by a cybersecurity attack or other form of attack. Control mechanisms may be installed and established to protect against specific cybersecurity attacks and other infiltrations. Machine learning and predictive analytics are used to more appropriately match specific attacks and threats against specific control mechanisms, accounting for dimensionality of control mechanisms. The matching of attack patterns and control mechanisms may use test scripts that operate on data pulled from the organization's systems of record. A factor analysis of information risk (FAIR) may be performed and visual threat models may be automatically generated that show the mapping between a threat actor, attack type, control environment including dimensionality, the targeted system, and the impact on the organization.

Automated real-time multi-dimensional cybersecurity threat modeling

A plurality of communicatively coupled, networked assets may be threatened or attacked by a cybersecurity attack. The operational resiliency of the computer network determines whether the cybersecurity attack leads to a shutdown of one or more assets, or even the entire computer network. A cybersecurity server selectively restricts and controls the data flow over the network and transforms a configurable, networked asset from a low, medium, and high cybersecurity mode. The cybersecurity server may reside on a firewall device or other networked device, and adjusts the cybersecurity mode based on a criticality score that measures the operational resiliency of the computer network. The criticality score changes as cybersecurity threats or attacks are identified and as mitigation strategies are implemented on the networked assets.

Cybersecurity&#x2014;operational resilience of computer networks

A system for using artificial intelligence to generate a computing network architecture diagram based on user inputs, applicable vulnerability/cyber threat data and internal/external compliance/audit regulation data. In addition, machine-learning techniques may be used that leverage previously implemented computing network architectures. The computing network architecture diagram may be generated absent a baseline diagram or the user inputs may define at least a portion of an initial/baseline network architecture diagram that is modified based on the vulnerability/cyber threat data, the internal/external compliance/audit regulation data and/or the previously implemented computing network architectures. In additional embodiments of the invention, new/emerging vulnerabilities and cyber threats are detected, and in real-time response, adjustments to the computing network infrastructure and determined and implemented.

Cybersecurity architectural network based on artificial intelligence

An information security system that includes an information security engine configured to monitor data transmissions within a network and to detect a first attack by a malicious software element. The information security engine is further configured to detect a second attack by the malicious software element within a predetermined time interval from the first attack and to transfer the malicious software element from the network to an emulated network in response to detecting the second attack. The information security engine is further configured to generate an attack log comprising behavior characteristics for attacks performed by the malicious software element in the emulated network and to train a machine learning model based on behavior characteristics from the attack log.

Network threat detection and information security using machine learning

A blind authenticator performs an authentication procedure with two devices that provides the convenience offered by password storage but avoids storing the passwords themselves. Generally, the blind authenticator stores on the two devices portions of different code generation algorithms. These algorithms on the devices are incomplete&#x2014;they may not execute properly on their own. During an authentication procedure, the blind authenticator communicates to the devices the remaining portions of these code generation algorithms so that the devices can execute their respective code generation algorithms. The devices then send the generated codes to the blind authenticator, which performs a code validation algorithm on the received codes to determine whether the codes are valid. The code validation algorithm is not sent to the devices, so the devices do not know what makes a code valid or invalid.

Growing community of inventors

Charlotte, NC, United States of America

Michael James Sbandi