US 11,991,210 B2
Machine learning-based techniques for identifying deployment environments and enhancing security thereof
Omer Karin, Tel Aviv (IL); Amit Magen, Netanya (IL); Moshe Israel, Ramat-Gan (IL); and Tamer Salman, Haifa (IL)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 26, 2020, as Appl. No. 17/080,204.
Prior Publication US 2022/0131900 A1, Apr. 28, 2022
Int. Cl. H04L 9/40 (2022.01); G06F 21/57 (2013.01); G06N 20/00 (2019.01)
CPC H04L 63/20 (2013.01) [G06F 21/57 (2013.01); G06F 21/572 (2013.01); G06N 20/00 (2019.01); G06F 2221/034 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for enhancing security for a deployment environment comprising a plurality of computing resources, the method comprising:
receiving data indicative of a usage of the plurality of computing resources in a particular deployment environment of a plurality of deployment environments, the plurality of deployment environments including a first deployment environment comprising a first stage of development and a second deployment environment comprising a second stage of development the plurality of deployment environments associated with respective stages of development;
generating a feature vector based on the data;
providing the feature vector as input to a machine learning-based classification model that identifies the particular deployment environment as comprising the first stage of development based on the feature vector, the machine learning-based classification model trained based on first past usage data comprising a first deployment environment label corresponding to the first stage of development and second past usage data comprising a second deployment environment label corresponding to the second stage of development; and
determining a security policy from a plurality of security policies that is applicable for the identified deployment environment.