Veracode has patented a system for identifying software flaws using a stacked classifier model ensemble, improving precision by 54.55%. The method involves k-fold cross validation, training multiple classifiers, and a logistic regression model. The system generates probabilities for software flaws and updates a database with the results. GlobalData’s report on Veracode 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 Veracode, Social data privacy protection was a key innovation area identified from patents. Veracode's grant share as of February 2024 was 47%. Grant share is based on the ratio of number of grants to total number of patents.
Software vulnerability detection using classifier ensemble and logistic regression
A recently granted patent (Publication Number: US11899800B2) outlines a method for identifying vulnerabilities or flaws in software components using a combination of classifiers and logistic regression models. The method involves training and testing a set of classifiers through k-fold cross-validation and then using probability vectors generated from this process to train a logistic regression model. By inputting a vector derived from a software development artifact into this ensemble of classifiers and the logistic regression model, probabilities are generated to indicate the presence of vulnerabilities or flaws in the software component. These probabilities are then used to update a database associated with the identity of the software component, providing valuable insights for developers and security professionals.
Furthermore, the patent details the use of natural language processing to extract tokens related to vulnerabilities or flaws from software development artifacts such as commit messages or bug reports. These tokens are then used to generate vectors representing the software components, aiding in the vulnerability assessment process. The method also involves associating labels with the software components based on the probabilities generated, indicating the presence of vulnerabilities or flaws. The patent extends to a computer-readable medium with executable instructions for implementing the method and an apparatus comprising a processor and instructions for training classifiers, generating probability values, and combining classifiers and logistic regression models to determine software component vulnerabilities. The apparatus also includes instructions for data collection from open-source software components, highlighting the practical application of the method in real-world scenarios.
To know more about GlobalData’s detailed insights on Veracode, 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.
