Granted Patent B2

US 12,499,218 · App. 17/995,365 · Granted Dec 16, 2025

Inventors: Xiao-Si Wang (London, GB); Jessica Welding (London, GB)

Assignee: British Telecommunications Public Limited Company

G06F21/552G06F2221/034

Abstract

Claims (28)

1 . A computer implemented malware protection method to protect computer systems in a population of network-connected computer systems, the method comprising:

identifying a plurality of clusters of the computer systems in the population of network-connected computer systems, wherein the computer systems within each of the plurality of clusters share at least one common characteristic;

determining a distribution of a metric of predicted final infection size for the population as a total number of computer systems infected by a propagation of a malware in the population, the distribution including predictions for infections originating with computer systems in the population, each predicted final infection size being determined by a forecasting simulation of malware propagation from an originating computer system in the population, the forecasting simulation of malware propagation being performed based on at least one malware propagation model defining at least a transmission rate of the malware between computer systems in the population determined to be in communication with each other, and a removal rate of computer systems being removed from a state of infection by the malware;

determining a plurality of ranges of final infection size from the distribution;

determining weighted associations between the identified plurality of clusters of computer systems and the determined ranges of final infection size based on numbers of incidences, during the forecasting simulation, that a malware infection beginning at originating computer systems in each cluster results in a final infection size within each range of final infection size, wherein determining the weighted associations comprises determining associations based on an association between each originating computer system in the population and a frequency of one or more final infection sizes arising from the forecasting simulation of malware propagation, and a cluster membership of the computer system, and determining the weighted associations for each determined association based on a frequency of occurrence of each final infection size within the determined ranges; and

deploying protective measures for one or more of the plurality of identified clusters of computer systems responsive to the weighted associations.

2 . The method of claim 1 , wherein the at least one common characteristic includes: a logical position or a physical position of the computer systems in the population; a network attribute of the computer systems in the population; a predetermined role or a function of the computer systems in the population; or a common type of device of the computer systems in the population.

3 . The method of claim 1 , wherein the at least one malware propagation model identifies interacting pairs of the computer systems in the population based on interactions corresponding to previous communication occurring between the computer systems in the pair.

4 . The method of claim 3 , wherein the forecasting simulation includes simulating, over a plurality of simulated time periods, a propagation of the malware from an originating computer system in the population, the simulating being based on a number of interactions per time period between each interacting pair of computer systems in the population, the transmission rate and the removal rate.

5 . The method of claim 1 , wherein the distribution includes predictions for infections originating with each computer system in the population.

6 . The method of claim 1 , wherein the plurality of ranges of final infection size is determined by:

determining a probability of each final infection size in the distribution to generate a signal indicating a range of probabilities for each final infection size, the signal being processed to reduce noise therein; and

determining the plurality of ranges of final infection size based on the signal.

7 . The method of claim 6 , wherein the plurality of ranges of final infection size are determined based on the signal by dividing the signal into the plurality of ranges based on an identification of local minima in the signal.

8 . The method of claim 1 , wherein the protective measures include one or more of: an anti-malware facility; a malware filter; a malware detector; a block, a preclusion or a cessation of interaction; or a reconfiguration of one or more computer systems.

9 . A computer system comprising:

a processor and memory storing computer program code for malware protection of computer systems in a population of network-connected computer systems, by:

identifying a plurality of clusters of the computer systems in the population of network-connected computer systems, wherein the computer systems within each of the plurality of clusters share at least one common characteristic;

determining a distribution of a metric of predicted final infection size for the population as a total number of computer systems infected by a propagation of a malware in the population, the distribution including predictions for infections originating with computer systems in the population, each predicted final infection size being determined by a forecasting simulation of malware propagation from an originating computer system in the population, the forecasting simulation of malware propagation being performed based on at least one malware propagation model defining at least a transmission rate of the malware between computer systems in the population determined to be in communication with each other, and a removal rate of computer systems being removed from a state of infection by the malware;

determining a plurality of ranges of final infection size from the distribution;

determining weighted associations between the identified plurality of clusters of computer systems and the determined ranges of final infection size based on numbers of incidences, during the forecasting simulation, that a malware infection beginning at originating computer systems in each cluster results in a final infection size within each range of final infection size, wherein determining the weighted associations comprises determining associations based on an association between each originating computer system in the population and a frequency of one or more final infection sizes arising from the forecasting simulation of malware propagation, and a cluster membership of the computer system, and determining the weighted associations for each determined association based on a frequency of occurrence of each final infection size within the determined ranges; and

deploying protective measures for one or more of the plurality of identified clusters of computer systems responsive to the weighted associations.

10 . A non-transitory computer-readable storage medium storing computer program code to, when loaded into a computer system and executed thereon, cause the computer system to implement malware protection to protect computer systems in a population of network-connected computer systems, by:

identifying a plurality of clusters of the computer systems in the population of network-connected computer systems, wherein the computer systems within each of the plurality of clusters share at least one common characteristic;

determining a distribution of a metric of predicted final infection size for the population as a total number of computer systems infected by a propagation of a malware in the population, the distribution including predictions for infections originating with computer systems in the population, each predicted final infection size being determined by a forecasting simulation of malware propagation from an originating computer system in the population, the forecasting simulation of malware propagation being performed based on at least one malware propagation model defining at least a transmission rate of the malware between computer systems in the population determined to be in communication with each other, and a removal rate of computer systems being removed from a state of infection by the malware;

determining a plurality of ranges of final infection size from the distribution;

determining weighted associations between the identified plurality of clusters of computer systems and the determined ranges of final infection size based on numbers of incidences, during the forecasting simulation, that a malware infection beginning at originating computer systems in each cluster results in a final infection size within each range of final infection size, wherein determining the weighted associations comprises determining associations based on an association between each originating computer system in the population and a frequency of one or more final infection sizes arising from the forecasting simulation of malware propagation, and a cluster membership of the computer system, and determining the weighted associations for each determined association based on a frequency of occurrence of each final infection size within the determined ranges; and

deploying protective measures for one or more of the plurality of identified clusters of computer systems responsive to the weighted associations.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (85)