US-20260127269-A1 - SYSTEM FOR DETECTION OF UNAUTHORIZED COMPUTER CODE USING AN ARTIFICIAL INTELLIGENCE-BASED ANALYZER

US20260127269A1US 20260127269 A1US20260127269 A1US 20260127269A1US-20260127269-A1

Abstract

A system is provided for detection of unauthorized computer code using an artificial intelligence-based analyzer. The system may include an artificial intelligence-based analyzer configured to receive various data and metadata from a user computing device when the user computing device is used to capture a scannable code using an image capture device. The system may, using the AI-based engine, compare the scanned code with a pool or repository of previously scanned code to determine whether the code has been scanned before. The repository may further comprise various types of metadata regarding the scanned code, such as success rate, usual scanning location, embedded resources or links within the code, timestamps for when the code was previously scanned, and/or the like. Based on the analysis of the scanned code, the system may present a notification on the user computing device that indicates whether the scanned code is potentially unsafe to execute.

Inventors

Manoj Kumar C M

Assignees

BANK OF AMERICA CORPORATION

Dates

Publication Date: 20260507
Application Date: 20251219

Claims (20)

1 . A system for detection of unauthorized computer code using an artificial intelligence-based analyzer, wherein the system is structured for processing a scannable code image, detecting inconsistent metadata, and preventing execution of unauthorized code to prevent compromise of the security of a user computing device, the system comprising: a processing device; and a non-transitory storage device containing instructions when executed by the processing device, causes the processing device to perform the steps of: receiving, from the user computing device, image data associated with a scannable code; extracting metadata associated with the scannable code by accessing a Uniform Resource Identifier or text executable code associated with the scannable code; processing the image data and metadata using an artificial intelligence analyzer, wherein processing the data and metadata comprises comparing the scannable code to one or more entries in a historical scannable code repository, wherein processing the image data and the metadata further comprises: converting pixels of the image data into a matrix of binary values based on predetermined significant bits in the image data; and based on processing the image data and metadata, determining whether the scannable code matches an entry of the one or more entries in the historical scannable code repository; wherein in response to detecting one or more inconsistencies between the metadata associated with the scannable code and metadata associated with an entry of the one or more entries of the historical scannable code repository: determining that the scannable code is unauthentic and unsafe to execute; and automatically blocking a processing activity associated with the scanning of the scannable code at the user computing device; or wherein in response to determining that the scannable code is safe to execute, presenting a notification on the user computing device, the notification indicating whether the scannable code is safe to execute, and wherein the notification comprises a visual indicator indicating that the scannable code is safe to execute.
2 . The system of claim 1 , wherein processing the data and metadata further comprises: converting the pixels of the image data into the matrix of binary values by executing a bit-wise matrix conversion of the scannable code using a convolutional neural network to generate a scannable code matrix; and executing a local search of the historical scannable code repository based on the scannable code matrix using an iterative deepening depth first search algorithm; wherein each of the one or more entries in the historical scannable code repository is associated with a historical scanned code, wherein each historical scanned code is stored as a hash of predetermined relevant bits and metadata associated with the historically scanned code.
3 . The system of claim 2 , wherein processing the data and metadata further comprises: identifying one or more parameters from the metadata; and executing a global search of the historical scannable code repository based on the one or more parameters using a simulated annealing process.
4 . The system of claim 3 , wherein the non-transitory storage device further contains instructions which when executed by the processing device cause the processing device to: optimize the scannable code based on (i) the types of metadata associated with the scannable code, and (ii) the quantity of metadata associated with the scannable code; and classify the scannable code based on the types of metadata associated with the scannable code.
5 . The system of claim 1 , wherein processing the data and metadata further comprises computing a confidence score associated with the scannable code, wherein the confidence score is computed based on one or more factors, the one or more factors comprising at least one of a usual location associated with the scannable code, an entity name or identifier associated with the scannable code, and an access frequency or pattern associated with the scannable code.
6 . The system of claim 1 , wherein the non-transitory storage device further contains instructions which when executed by the processing device cause the processing device to: determine a geographic location associated with the user computing device; determine a plurality of additional scannable codes within a predetermined proximity of the geographic location; and construct a display of a viewable map at a user dashboard of the user computing device such that locations of the plurality of additional scannable codes are pinned to viewable map.
7 . The system of claim 1 , wherein the metadata comprises text associated with the scannable code, location where the user computing device scanned the scannable code, access pattern, scan frequency, a timestamp indicating when the user computing device scanned the scannable code and/or type of function executed by the scannable code.
8 . A computer program product for detection of unauthorized computer code using an artificial intelligence-based analyzer, wherein the computer program product is structured for processing a scannable code image, detecting inconsistent metadata, and preventing execution of unauthorized code to prevent compromise of the security of a user computing device, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to perform the steps of: receiving, from the user computing device, image data associated with a scannable code; extract metadata associated with the scannable code by accessing a Uniform Resource Identifier or text executable code associated with the scannable code; processing the image data and metadata using an artificial intelligence analyzer, wherein processing the data and metadata comprises comparing the scannable code to one or more entries in a historical scannable code repository, wherein processing the image data and the metadata further comprises: converting pixels of the image data into a matrix of binary values based on predetermined significant bits in the image data; based on processing the image data and metadata, determining whether the scannable code matches an entry of the one or more entries in the historical scannable code repository; wherein in response to detecting one or more inconsistencies between the metadata associated with the scannable code and metadata associated with an entry of the one or more entries of the historical scannable code repository: determining that the scannable code is unauthentic and unsafe to execute; and automatically blocking a processing activity associated with the scanning of the scannable code at the user computing device; or wherein in response to determining that the scannable code is safe to execute, presenting a notification on the user computing device, the notification indicating whether the scannable code is safe to execute, and wherein the notification comprises a visual indicator indicating that the scannable code is safe to execute.
9 . The computer program product of claim 8 , wherein processing the data and metadata further comprises: converting the pixels of the image data into the matrix of binary values by executing a bit-wise matrix conversion of the scannable code using a convolutional neural network to generate a scannable code matrix; and executing a local search of the historical scannable code repository based on the scannable code matrix using an iterative deepening depth first search algorithm; wherein each of the one or more entries in the historical scannable code repository is associated with a historical scanned code, wherein each historical scanned code is stored as a hash of predetermined relevant bits and metadata associated with the historically scanned code.
10 . The computer program product of claim 9 , wherein processing the data and metadata further comprises: identifying one or more parameters from the metadata; and executing a global search of the historical scannable code repository based on the one or more parameters using a simulated annealing process.
11 . The computer program product of claim 10 , wherein the computer program product further comprises code causing the apparatus to perform the steps of: optimizing the scannable code based on (i) the types of metadata associated with the scannable code, and (ii) the quantity of metadata associated with the scannable code; and classifying the scannable code based on the types of metadata associated with the scannable code.
12 . The computer program product of claim 8 , wherein processing the data and metadata further comprises computing a confidence score associated with the scannable code, wherein the confidence score is computed based on one or more factors, the one or more factors comprising at least one of a usual location associated with the scannable code, an entity name or identifier associated with the scannable code, and an access frequency or pattern associated with the scannable code.
13 . The computer program product of claim 8 , wherein the computer program product further comprises code causing the apparatus to perform the steps of: determining a geographic location associated with the user computing device; determining a plurality of additional scannable codes within a predetermined proximity of the geographic location; and constructing a display of a viewable map at a user dashboard of the user computing device such that locations of the plurality of additional scannable codes are pinned to viewable map.
14 . A computer-implemented method for detection of unauthorized computer code using an artificial intelligence-based analyzer, wherein the computer-implemented method is structured for processing a scannable code image, detecting inconsistent metadata, and preventing execution of unauthorized code to prevent compromise of the security of a user computing device, the computer-implemented method comprising: receiving, from the user computing device, image data associated with a scannable code; extract metadata associated with the scannable code by accessing a Uniform Resource Identifier or text executable code associated with the scannable code; processing the image data and metadata using an artificial intelligence analyzer, wherein processing the data and metadata comprises comparing the scannable code to one or more entries in a historical scannable code repository, wherein processing the image data and the metadata further comprises: converting pixels of the image data into a matrix of binary values based on predetermined significant bits in the image data; and based on processing the image data and metadata, determining whether the scannable code matches an entry of the one or more entries in the historical scannable code repository; wherein in response to detecting one or more inconsistencies between the metadata associated with the scannable code and metadata associated with an entry of the one or more entries of the historical scannable code repository: determining that the scannable code is unauthentic and unsafe to execute; and automatically blocking a processing activity associated with the scanning of the scannable code at the user computing device; or wherein in response to determining that the scannable code is safe to execute, presenting a notification on the user computing device, the notification indicating whether the scannable code is safe to execute, and wherein the notification comprises a visual indicator indicating that the scannable code is safe to execute.
15 . The computer-implemented method of claim 14 , wherein processing the data and metadata further comprises: converting the pixels of the image data into the matrix of binary values by executing a bit-wise matrix conversion of the scannable code using a convolutional neural network to generate a scannable code matrix; and executing a local search of the historical scannable code repository based on the scannable code matrix using an iterative deepening depth first search algorithm; wherein each of the one or more entries in the historical scannable code repository is associated with a historical scanned code, wherein each historical scanned code is stored as a hash of predetermined relevant bits and metadata associated with the historically scanned code.
16 . The computer-implemented method of claim 15 , wherein processing the data and metadata further comprises: identifying one or more parameters from the metadata; and executing a global search of the historical scannable code repository based on the one or more parameters using a simulated annealing process.
17 . The computer-implemented method of claim 16 , wherein the computer-implemented method further comprises: optimizing the scannable code based on (i) the types of metadata associated with the scannable code, and (ii) the quantity of metadata associated with the scannable code; and classifying the scannable code based on the types of metadata associated with the scannable code.
18 . The computer-implemented method of claim 14 , wherein processing the data and metadata further comprises computing a confidence score associated with the scannable code, wherein the confidence score is computed based on one or more factors, the one or more factors comprising at least one of a usual location associated with the scannable code, an entity name or identifier associated with the scannable code, and an access frequency or pattern associated with the scannable code.
19 . The computer-implemented method of claim 14 , wherein the computer-implemented method further comprises: determining a geographic location associated with the user computing device; determining a plurality of additional scannable codes within a predetermined proximity of the geographic location; and constructing a display of a viewable map at a user dashboard of the user computing device such that locations of the plurality of additional scannable codes are pinned to viewable map.
20 . The computer-implemented method of claim 14 , wherein the metadata comprises text associated with the scannable code, location where the user computing device scanned the scannable code, access pattern, scan frequency, a timestamp indicating when the user computing device scanned the scannable code and/or type of function executed by the scannable code.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is a continuation of and claims the benefit of priority to U.S. Patent Application No. 18/504,386, filed November 8, 2023, and of the same title; the contents of which are also incorporated herein by reference. TECHNOLOGICAL FIELD Example embodiments of the present disclosure relate to a system for detection of unauthorized computer code using an artificial intelligence-based analyzer. BACKGROUND There is a need for a secure, reliable way to detect potentially unauthorized code. BRIEF SUMMARY The following presents a simplified summary of one or more embodiments of the present invention, in order to provide a basic understanding of such embodiments. This summary is not an extensive overview of all contemplated embodiments and is intended to neither identify key or critical elements of all embodiments nor delineate the scope of any or all embodiments. Its sole purpose is to present some concepts of one or more embodiments of the present invention in a simplified form as a prelude to the more detailed description that is presented later. A system is provided for detection of unauthorized computer code using an artificial intelligence-based analyzer. In particular, the system may include an artificial intelligence-based engine or module that may be configured to receive various data and/or metadata from a user computing device when the user computing device is used to execute certain functions, such as capturing a scannable code using an image capture device. The system may, using the AI-based engine, compare the scanned code with a pool or repository of previously scanned code to determine whether the code has been scanned before. The repository may further comprise various types of metadata regarding the scanned code, such as success rate, usual scanning location, embedded resources or links within the code, timestamps for when the code was previously scanned, and/or the like. Based on the analysis of the scanned code, the system may present a notification on the user computing device that indicates whether the scanned code is potentially unsafe to execute. In this way, the system may provide a way to proactively prevent users from executing unauthorized code. Accordingly, embodiments of the present disclosure provide a system for detection of unauthorized computer code using an artificial intelligence-based analyzer, the system comprising a processing device; a non-transitory storage device containing instructions when executed by the processing device, causes the processing device to perform the steps of detecting that a user computing device has scanned a scannable code; receiving, from the user computing device, data and metadata associated with the scannable code; processing the data and metadata using an artificial intelligence analyzer, wherein processing the data and metadata comprises comparing the scannable code to one or more entries in a historical scannable code repository; based on processing the data and metadata, determining whether the scannable code matches an entry of the one or more entries in the historical scannable code repository; and presenting a notification on the user computing device, the notification indicating whether the scannable code is safe to execute. In some embodiments, processing the data and metadata further comprises executing a bit-wise matrix conversion of the scannable code using a convolutional neural network to generate a scannable code matrix; and executing a local search of the historical scannable code repository based on the scannable code matrix using an iterative deepening depth first search algorithm. In some embodiments, processing the data and metadata further comprises identifying one or more parameters from the metadata; and executing a global search of the historical scannable code repository based on the one or more parameters using a simulated annealing process. In some embodiments, the one or more parameters comprises location data of the user computing device and a timestamp indicating when the user computing device scanned the scannable code. In some embodiments, processing the data and metadata further comprises computing a confidence score associated with the scannable code, wherein the confidence score is computed based on one or more factors, the one or more factors comprising at least one of a usual location associated with the scannable code, an entity name or identifier associated with the scannable code, and an access frequency or pattern associated with the scannable code. In some embodiments, processing the data and metadata comprises determining that the scannable code is unsafe to execute; and automatically blocking the execution of the scannable code on the user computing device. In some embodiments, processing the data and metadata comprises determining that the scannable code is safe to execute; and wherein the notification comprises a visual indicator indicating that the scan