Vectra AI has patented a method for detecting malicious network activity using a GraphMDN approach. The method involves collecting network data, generating a graph representation, and training a graph mixture density neural network to analyze the data and generate detection results. GlobalData’s report on Vectra AI gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Vectra AI, IoT network security was a key innovation area identified from patents. Vectra AI's grant share as of February 2024 was 55%. Grant share is based on the ratio of number of grants to total number of patents.
Malicious network activity detection using graphmdn
A recently granted patent (Publication Number: US11880764B2) outlines a method for network activity analysis using a graph mixture density neural network. The method involves collecting network activity data, generating a graph representation of the activity, and training a neural network using a graph convolution process to analyze the data. The neural network generates multiple Gaussian distributions, each with mixing coefficients, to evaluate additional network activity and generate detection results. These results can identify potential staging points within a network where data may be collected before being sent to an external host for exfiltration.
Furthermore, the patent describes the use of unique identifiers, communication sources and destinations, data amounts, communication characteristics, and timestamps in the network activity data. The method also includes updating the graph representation with new data and maintaining it using various identifiers and matrices. Additionally, the patent covers the implementation of the method on a non-transitory computer-readable medium and a system comprising memory and a processor to execute the instructions for network activity analysis. The system utilizes the graph mixture density neural network to process embeddings generated from the graph representation, enabling the detection of potential threats within a network based on the analysis of network activity against distributions generated by the neural network.
To know more about GlobalData’s detailed insights on Vectra AI, buy the report here.
Premium 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, 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.
