# US 2022/0046047 A1 · Monitoring and Preventing Remote User Automated Cyber Attacks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0046047 A1
- Document ID: US20220046047A1
- Status: Published application
- Kind: A1
- Application number: 16/988,863
- Filed: 2020-08-10
- Published: 2022-02-10
- Earliest claimed: 2020-08-10
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: Patrick Lewis
- Web page: https://patentgrep.com/patent/US20220046047A1

## CPC

- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/1433: {Vulnerability analysis}
- G06F 9/452: {Remote windowing, e.g. X-Window System, desktop virtualisation (protocols for virtual reality H04L67/131)}
- G06F 9/45558: {Hypervisor-specific management and integration aspects}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 21/554: {involving event detection and direct action}
- G06N 20/00: Machine learning
- H04L 63/0227: {Filtering policies (mail message filtering H04L51/212)}
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- H04L 63/1441: {Countermeasures against malicious traffic (countermeasures against attacks on cryptographic mechanisms H04L9/002)}
- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- G06F 2009/45587: {Isolation or security of virtual machine instances}
- G06F 2009/45595: {Network integration; Enabling network access in virtual machine instances}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Aspects of the disclosure relate to monitoring virtual desktops accessed by devices at remote locations using machine-learning models to mitigate potential cyber-attacks. In some embodiments, a computing platform may monitor data associated with a series of activities from a virtual desktop accessed by a remote computing device. Subsequently, the computing platform may detect new activity data on the virtual desktop accessed by the remote computing device, and evaluate the new activity data relative to the data associated with the series of activities, wherein evaluating includes applying a machine learning model to the new activity data. Based on evaluating the new activity data, the computing platform may determine if the new activity data is indicative of a potential cyber-attack. In response to determining that the new activity data is indicative of a potential cyber-attack, the computing platform may initiate one or more security response actions.

## Claims

### Claim 1

A computing platform, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
monitor data associated with a series of activities from a virtual desktop accessed by a remote computing device;
detect new activity data on the virtual desktop accessed by the remote computing device;
evaluate the new activity data relative to the data associated with the series of activities, wherein evaluating includes applying a machine learning model to the new activity data;
determine if the new activity data is indicative of a potential cyber-attack based on evaluating the new activity data relative to the data associated with series of activities; and
in response to determining that the new activity data is indicative of a potential cyber-attack, initiate one or more security response actions.

### Claim 2 (depends on 1)

The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
train the machine learning model to the data associated with the series of activities to establish one or more factors for an anomalous virtual desktop accessed by the remote computing device, wherein an anomalous session is associated with a potential cyber-attack.

### Claim 3 (depends on 2)

The computing platform of claim 2, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
in response to determining that the new activity data is not indicative of a potential cyber-attack, update the machine learning model with the new activity data.

### Claim 4 (depends on 2)

The computing platform of claim 2, wherein training the machine learning model to the data associated with the series of activities to establish the one or more factors for the anomalous virtual desktop accessed by the remote computing device comprises training the machine learning model to the data associated with the series of activities to establish a type of content viewed as a factor of the one or more factors, a number of times content is viewed as a factor of the one or more factors, or a repetition of actions as a factor of the one or more factors.

### Claim 5 (depends on 2)

The computing platform of claim 2, wherein training the machine learning model to the data associated with the series of activities to establish the one or more factors for the anomalous virtual desktop accessed by the remote computing device comprises training the machine learning model to the data associated with the series of activities to establish a timing of the new activity data on the virtual desktop accessed by the remote computing device as a factor of the one or more factors, a sensitivity of content being viewed as a factor of the one or more factor, or a pattern of actions associated with the new activity data on the virtual desktop accessed by the remote computing device as a factor of the one or more factors.

### Claim 6 (depends on 2)

The computing platform of claim 2, wherein training the machine learning model to the data associated with the series of activities to establish the one or more factors for the anomalous virtual desktop accessed by the remote computing device comprises training the machine learning model to the data associated with the series of activities to establish a change from creating content to viewing content as a factor of the one or more factors.

### Claim 7 (depends on 2)

The computing platform of claim 2, wherein training the machine learning model to the data associated with the series of activities to establish the one or more factors for the anomalous virtual desktop accessed by the remote computing device comprises training the machine learning model to the data associated with the series of activities to establish one or more user account settings as a factor of the one or more factors.

### Claim 8 (depends on 2)

The computing platform of claim 2, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
monitor data associated with a series of local activities at a local computing device from a user account associated with the virtual desktop,
wherein the machine learning model is trained based on the data associated with the series of activities and the new activity data relative to the data associated with the series of local activities.

### Claim 9 (depends on 1)

The computing platform of claim 1, wherein detecting the new activity data includes detecting an idle state at the remote computing device prior to detecting the new activity data and after receiving the data associated with the series of activities.

### Claim 10 (depends on 1)

The computing platform of claim 1, wherein initiating the one or more security response actions includes transmitting a security response alert to a data loss prevention computing device.

### Claim 11 (depends on 10)

The computing platform of claim 10, wherein the security response alert includes one or more components of information associated with the new activity data and one or more components of information relating to an indication of a potential cyber-attack.

### Claim 12 (depends on 1)

The computing platform of claim 1, wherein initiating the one or more security response actions includes transmitting an authentication communication to the remote computing device, and receiving a responsive authentication from the remote computing device.

### Claim 13 (depends on 1)

The computing platform of claim 1, wherein initiating the one or more security response actions includes transmitting a security response alert to a data loss prevention computing device, and wherein transmitting the security response alert causes a screen mirroring session of the remote computing device to initiate at a display of the data loss prevention computing device.

### Claim 14 (depends on 1)

The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive a confirmation that the new activity is indicative of a suspicious activity; and
responsive to receiving the confirmation, terminate a connection at the remote computing device to a private network.

### Claim 15

A method, comprising:
at a computing platform comprising at least one processor, a communication interface, and memory:
monitoring, by the at least one processor, data associated with a series of activities from a virtual desktop accessed by a remote computing device;
detecting, by the at least one processor, new activity data on the virtual desktop accessed by the remote computing device;
evaluating, by the at least one processor, the new activity data relative to the data associated with the series of activities, wherein evaluating includes applying a machine learning model to the new activity data;
determining, by the at least one processor, if the new activity data is indicative of a potential cyber-attack based on evaluating the new activity relative to the data associated with the series of activities; and
in response to determining that the new activity data is indicative of a potential cyber-attack, initiating, by the at least one processor, one or more security response actions.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
training the machine learning model to the data associated with the series of activities to establish one or more factors for an anomalous remote session of the virtual desktop accessed by the remote computing device, wherein an anomalous session is associated with a potential cyber-attack.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
monitoring data associated with a series of local activities at a local computing device from a user account associated with the virtual desktop,
wherein the machine learning model is trained based on the data associated with the series of activities and the new activity data relative to the data associated with the series of local activities.

### Claim 18 (depends on 15)

The method of claim 15, wherein initiating the one or more security response actions includes transmitting a security response alert to a data loss prevention computing device.

### Claim 19 (depends on 15)

The method of claim 15, wherein detecting the new activity data includes detecting an idle state at the remote computing device prior to detecting the new activity data and after receiving the data associated with the series of activities.

### Claim 20

One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:
monitor data associated with a series of activities from a remote user account at a remote computing device;
detect new activity data from the remote user account at the remote computing device;
evaluate the new activity data relative to the data associated with the series of activities;
determine if the new activity data is indicative of a potential cyber-attack based on evaluating the new activity relative to the series of activities; and
in response to determining that the new activity data is indicative of a potential cyber-attack, initiate one or more security response actions.
