US 12,436,827 B2
Systems and methods for predicting which software vulnerabilities will be exploited by malicious hackers to prioritize for patching
Paulo Shakarian, Tempe, AZ (US); Mohammed Almukaynizi, Tempe, AZ (US); Jana Shakarian, Tempe, AZ (US); Eric Nunes, Tempe, AZ (US); Krishna Dharaiya, Tempe, AZ (US); Manoj Balasubramaniam Senguttuvan, Tempe, AZ (US); and Alexander Grimm, Tempe, AZ (US)
Assigned to Arizona Board of Regents on Behalf of Arizona State University, Tempe, AZ (US)
Filed by Arizona Board of Regents on Behalf of Arizona State University, Tempe, AZ (US)
Filed on Oct. 29, 2023, as Appl. No. 18/496,880.
Application 18/496,880 is a division of application No. 16/640,878, granted, now 11,892,897, previously published as PCT/US2018/057812, filed on Oct. 26, 2018.
Claims priority of provisional application 62/581,123, filed on Nov. 3, 2017.
Prior Publication US 2024/0134728 A1, Apr. 25, 2024
Int. Cl. G06F 21/57 (2013.01); G06F 11/00 (2006.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06F 21/54 (2013.01); G06F 21/55 (2013.01)
CPC G06F 11/008 (2013.01) [G06F 18/2148 (2023.01); G06F 18/24 (2023.01); G06F 21/54 (2013.01); G06F 21/552 (2013.01); G06F 21/577 (2013.01)] 5 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium storing instructions that cause a processor to:
generate a learned function referencing features associated with a plurality of datasets defining software vulnerabilities and at least one machine learning algorithm; and
evaluate accuracy of the learned function by applying a portion of the plurality of datasets associated with software vulnerabilities to the learned function, including
predicting a likelihood of exploitation associated with a software vulnerability including computation of an associated class label, wherein the likelihood of exploitation predicts an actual exploitation of the respective software vulnerabilities before disclosure based on hacker communications from training data.