Exabeam. has been granted a patent for a method that utilizes machine learning to automatically classify user accounts in IT networks. The system analyzes identity management key-value pairs to determine the likelihood of accounts being service accounts, enhancing security analytics and improving classification accuracy. GlobalData’s report on Exabeam gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Exabeam, DNS monitoring was a key innovation area identified from patents. Exabeam's grant share as of June 2024 was 90%. Grant share is based on the ratio of number of grants to total number of patents.

Automated classification of user accounts in it networks

Source: United States Patent and Trademark Office (USPTO). Credit: Exabeam Inc

The patent US12034732B2 outlines a method and system for the automatic classification of user accounts within an entity's IT network, utilizing identity management key-value pairs. The process begins with training a statistical model to associate these key-value pairs with the likelihood of being linked to service user accounts. This involves parsing account data from an identity management system, where user accounts are manually classified as either service or human accounts. The model employs machine learning techniques to evaluate unclassified accounts by representing them as N-dimensional vectors based on their associated key-value pairs. If the calculated probability of an account being a service user exceeds a predetermined threshold, it is classified accordingly.

Additionally, the method incorporates context-specific rules to enhance the accuracy of security analytics alerts. These rules help identify instances where accounts classified as service users are actually human accounts. The system also includes mechanisms for adjusting classification thresholds based on equal error rates, allowing for more nuanced decision-making. If the probability falls below certain thresholds, accounts may be classified as human or marked as undetermined. The statistical model can be constructed using Bernoulli Naïve Bayes modeling, and the system is designed to identify discrepancies between automated and manual classifications, thereby improving overall classification accuracy and security within the IT network.

To know more about GlobalData’s detailed insights on Exabeam, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.