ON-LINE BEHAVIORAL ANALYSIS ENGINE IN MOBILE DEVICE WITH MULTIPLE ANALYZER MODEL PROVIDERS

摘要

Methods, systems and devices for generating data models in a client-cloud communication system include applying machine learning techniques to generate first-order classifier models that describe a cloud corpus of behavior vectors You may. These vectors may be analyzed to identify in the first-line classifier models factors with the highest probability that enable the mobile device to better determine whether the mobile device behavior is malicious or positive. Based on this analysis, it is possible to identify significantly fewer factors and data points as relevant to enable the mobile device to better determine whether the mobile device behavior is malignant or benign based on the determined factors A second class of classifier models may be generated. A mobile device classifier module may be created based on the second class of classifier models and may be made available for download by mobile devices that include devices that contribute to behavior vectors.