Back to results
US 9,672,355 B2Granted
Automated behavioral and static analysis using an instrumented sandbox and machine learning classification for mobile security
AssigneeVeracode, Inc.
InventorsTheodora Heather Titonis, Nelson Roberto Manohar-Alers, Christopher John Wysopal
Life of this patent
Estimating the term…
Abstract
The present system includes a computer-networked system that allows mobile subscribers, and others, to submit mobile applications to be analyzed for anomalous and malicious behavior using data acquired during the execution of the application within a highly instrumented and controlled environment for which the analysis relies on per-execution as well as comparative aggregate data across many such executions from one or more subscribers.
Claims45
A method for assessing the quality of mobile applications, the method comprising:
- providing a computer networked environment comprising a cloud-based service for mobile devices that when operated:
- performs a static analysis risk assessment of binary code associated with a mobile application being submitted by a submission source, the static analysis comprising de-compiling the binary code to obtain corresponding source code and determining from the source code at least one capability of the binary code;
- examines execution behavior of the mobile application within an instrumented sandbox environment;
- aggregates analysis of the execution behavior and static analysis to generate a feature vector comprising:
- (i) a network summary feature, (ii) an operating system based behavioral feature, and (iii) a static analysis feature;
- and
- performs classification using the feature vector, yielding predictor statistics describing quality and vulnerability characteristics of mobile application.
4 more elements
Dependencies are inferred from the claim text.