Ventech Solutions has been granted two patents for the method and systems offered in its Valholla solution. Valholla, a Ventech Solutions product, is a development, security and operations (DevSecOps) and governance tool for enterprise visibility, control and intelligence. The solution leverages APIs to integrate with existing continuous integration and continuous delivery (CI/CD) pipelines, so there’s no need to replace existing tools. With Valholla, Ventech Solutions clients can centrally control and manage information technology (IT) deployment automation, security and functional testing, as well as cloud cost optimization from a single interface.
Also Read: New Wireless Security Tool Combats Stalkers, Skimmers and Hackers
“As a team, we are thrilled to announce the patents awarded to the methods that make up the Valholla solution,” said Steve Veneruso, chief technology officer at Ventech Solutions. “Valholla is a state-of-the-art tool that allows our clients to save time and resources, reduce costs, enhance security and eliminate manual steps and processes across the enterprise.”
Valholla ensures adherence to standards, streamlines deployment processes, consolidates data from numerous tools and intuitively presents the data in a user-friendly interface. This results in greater overall efficiencies and significantly reduces manually induced errors.
U.S. Patent Nos. 11438339 and 11436335 were granted on September 6, 2022, by the United States Patent and Trademark Office (USPTO).
Method and system for neural network based data analytics in software security vulnerability testing
Patent 11438339
A method and system for implementing AI based neural networks for data analytics in dynamic testing of security vulnerability of cloud-based enterprise software applications. The method comprises directing, to a software program under execution, a series of attack vectors; diagnosing an at least a first set of results associated with the software program under execution as comprising one of a security vulnerability and not a security vulnerability, the at least a first set of results produced based at least in part on the attack vectors; and training a machine learning neural network classifier in accordance with a supervised classification that identifies false positive vulnerability defects of the at least a first set of results to produce a trained classifier, the neural network classifier including an input and an output layers connected via at least one intermediate layer that is configured in accordance with an initial matrix of weights.