# US 12,120,141 B2 · Security scores > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,120,141 B2 - Document ID: US12120141B2 - Status: Granted - Kind: B2 - Application number: 17/387,741 - Filed: 2021-07-28 - Published: 2022-02-03 - Granted: 2024-10-15 - Earliest claimed: 2020-07-28 - Assignees: Hewlett-Packard Development Company, L.P. - Applicants: Hewlett-Packard Development Company, L.P. - Inventors: Narendra Kumar Chincholikar; Sanket Anavkar; Vaibhav Tarange; Manohar Lal Kalwani - Web page: https://patentgrep.com/patent/US12120141B2 ## CPC - H04L 63/1433: {Vulnerability analysis} - G06N 5/04: Inference or reasoning models - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract In an example implementation according to aspects of the present disclosure, a system, method, and storage medium to identify and score security vulnerabilities is disclosed. A memory and a processor receive security-related data from a plurality of client computing devices, create a security score for each the client computing devices. The processor identifies a subset of the client computing devices with security scores surpassing a threshold and remediates a security vulnerability on each of the subset. ## Claims ### Claim 1 A system comprising: a memory comprising instructions; and a processor communicatively coupled to the memory wherein the instructions when executed cause the processor to: receive security-related data from a plurality of client computing devices; for each client computing device of the plurality of client computing devices, evaluate a plurality of categorical attack methods using the security-related data; determine, as a plurality of probability values, a probability value for each categorical attack method of the plurality of categorical attack methods; and create, based on an aggregation of the plurality of probability values, an overall security score using an artificial intelligent software model; identify, responsive to creation of the overall security score for each of the plurality of client computing devices, a subset of the plurality of client computing devices with overall security scores surpassing a threshold; and remediate a security vulnerability on each of the subset of the plurality of client computing devices. ### Claim 2 (depends on 1) The system of claim 1, the instructions when executed further cause the processor to: identify a second subset of the plurality of client computing devices; and determine an organizational security score based on the overall security scores of each of the second subset of the plurality of client computing devices. ### Claim 3 (depends on 2) The system of claim 2, the instructions when executed further cause the processor to: render a visual representation of the organizational security score; and render a visual representation of the overall security scores of the second subset of the plurality of client computing devices. ### Claim 4 (depends on 1) The system of claim 1, wherein the artificial intelligent software model comprises a Bayesian network model. ### Claim 5 (depends on 1) The system of claim 1, the instructions when executed cause the processor to send an endpoint management instruction to enable an antivirus program to remediate the security vulnerability. ### Claim 6 A method comprising: receiving, with a processor, security-related data from a plurality of client computing devices; for each client computing device of the plurality of client computing devices, evaluating, with the processor, a plurality of categorical attack methods using the security-related data; determining, with the processor, as a plurality of probability values, a probability value for each categorical attack method of the plurality of categorical attack methods; and creating, with the processor, an overall security score using an artificial intelligent software model; identifying, with the processor, a subset of the plurality of client computing devices with overall security scores surpassing a threshold; rendering, with the processor, a representation for each of the subset of the plurality of client computing devices and a corresponding overall security score to each of the subset on a dashboard; and remediating, with the processor, a security vulnerability on each of the subset of the plurality of client computing devices. ### Claim 7 (depends on 6) The method of claim 6, further comprising: identifying, with the processor, a second subset of the plurality of client computing devices; and determining, with the processor, an organizational security score based on the overall security scores of each of the second subset of the plurality of client computing devices. ### Claim 8 (depends on 7) The method of claim 7, further comprising: rendering, with the processor, a visual representation of the organizational security score; and rendering, with the processor, a visual representation of the overall security scores of the second subset of the plurality of client computing devices. ### Claim 9 (depends on 6) The method of claim 6, wherein creating, with the processor, the overall security score using the artificial intelligent software model includes creating the overall security score using a Bayesian network model. ### Claim 10 (depends on 6) The method of claim 6, wherein the remediating the security vulnerability comprises sending, with the processor, an endpoint management instruction to enable an antivirus program. ### Claim 11 A non-transitory computer readable medium comprising instructions executable by a processor to: receive a first security-related data from a plurality of client computing devices; for each client computing device of the plurality of client computing devices, evaluate a plurality of categorical attack methods using the security-related data; determine, as a plurality of probability values, a probability value for each categorical attack method of the plurality of categorical attack methods; and create, based on an aggregation of the plurality of probability values, a first security score using an artificial intelligent software model; identify a subset of the plurality of client computing devices with first security scores surpassing a threshold; receive a subsequent security-related data from a plurality of client computing devices; for each client computing device of the plurality of client computing devices, evaluate the plurality of categorical attack methods using the subsequent security-related data; determine, as a plurality of subsequent probability values, a subsequent probability value for each categorical attack method of the plurality of categorical attack methods; and create, based on a subsequent aggregation of the plurality of subsequent probability values, a subsequent security score using the artificial intelligent software model; identify a subsequent subset of the plurality of client computing devices with the difference of the subsequent security scores and the first security scores surpassing a second threshold; and render the subsequent subset of the plurality of client computing devices on a display. ### Claim 12 (depends on 11) The medium of claim 11 the instructions further comprising: identify a second subset of the plurality of client computing devices corresponding to an organization; and determine an organizational security score based on the subsequent security scores of each of the subsequent subset of the plurality of client computing devices. ### Claim 13 (depends on 12) The medium of claim 12 the further comprising: render a visual representation of the organizational security score; and render a visual representation of the subsequent security scores of the second subset of the plurality of client computing devices. ### Claim 14 (depends on 11) The medium of claim 11 wherein the artificial intelligent software model comprises Bayesian network model. ### Claim 15 (depends on 11) The medium of claim 11 remediating the security vulnerability comprises sending an endpoint management instruction to enable an antivirus program. ### Claim 16 (depends on 1) The system of claim 1, wherein the security-related data includes a plurality of device identifiers for the plurality of client computing devices, and wherein the instructions when executed cause the processor to identify the subset of the plurality of client computing devices using the plurality of device identifiers. ### Claim 17 (depends on 1) The system of claim 1, wherein the security-related data includes an installed version of security software. ### Claim 18 (depends on 1) The system of claim 1, wherein the security-related data includes an installed version of an operating system. ### Claim 19 (depends on 1) The system of claim 1, wherein the security-related data includes at least one of a dataset of information corresponding to an operational state of a corresponding client computing device or a device identifier of the corresponding client computing device. ### Claim 20 (depends on 1) The system of claim 1, wherein the plurality of categorical attack methods includes an operating system attack and a firmware attack, and wherein the plurality of probability values includes a probability value associated with the operating system attack and a probability value associated with the firmware attack.