Method and system for machine learning model testing and preventive measure recommendation

Abstract

Data-driven applications depend on training data obtained from multiple internal and external data sources. Hence poisoning of the training data can cause adverse effects in the data driven applications. Conventional methods identifies contaminated test samples and avert them from entering into the training. A generic approach covering all data-driven applications and all types of data poisoning attacks in an efficient manner is challenging. Initially, data aggregation is performed after receiving a ML application for testing. A plurality of feature vectors are extracted from the aggregated data and a poisoned data set is generated. A plurality of personas are generated and are further prioritized to obtain a plurality of attack personas. Further, a plurality of security assessment vectors are computed for each of the plurality of attack personas. A plurality of preventive measures are recommended for each of the plurality of attack personas based on the corresponding security assessment vector.