A distributed platform for intrusion detection system using data stream mining in a big data environment

With the growth of computer networks worldwide, there has been a greater need to protect local networks from malicious data that travel over the network. The increase in volume, speed, and variety of data requires a more robust, accurate intrusion detection system capable of analyzing a huge amount of data. This work proposes the creation of an intrusion detection system using stream classifiers and three classification layers—with and without a reduction in the number of features of the records and three classifiers in parallel with a voting system. The results obtained by the proposed system are compared against other models proposed in the literature, using two datasets to validate the proposed system. In all cases, gains in accuracy of up to 18.52% and 3.55% were obtained, using the datasets NSL-KDD and CICIDS2017, respectively. Reductions in classification time up to 35.51% and 94.90% were also obtained using the NSL-KDD and CICIDS2017 datasets, respectively.