With vast amounts of data being generated daily and the ever increasing interconnectivity of the world's internet infrastructures, a machine learning based Intrusion Detection Systems (IDS) has become a vital component to protect our economic and national security. Previous shallow learning and deep learning strategies adopt the single learning model approach for intrusion detection. The single learning model approach may experience problems to understand increasingly complicated data distribution of intrusion patterns. Particularly, the single deep learning model may not be effective to capture unique patterns from intrusive attacks having a small number of samples. In order to further enhance the performance of machine learning based IDS, we propose the Big Data based Hierarchical Deep Learning System (BDHDLS). BDHDLS utilizes behavioral features and content features to understand both network traffic characteristics and information stored in the payload. Each deep learning model in the BDHDLS concentrates its efforts to learn the unique data distribution in one cluster. This strategy can increase the detection rate of intrusive attacks as compared to the previous single learning model approaches. Based on parallel training strategy and big data techniques, the model construction time of BDHDLS is reduced substantially when multiple machines are deployed.

Wireless Sensor Networks (WSNs) are employed in many applications in order to collect data. One key challenge is to minimize energy consumption to prolong network lifetime. A scheme of making some nodes asleep and estimating their values according to the other active nodes' readings has been proved energy-efficient. For the purpose of improving the precision of estimation, we propose two powerful estimation models, Data Estimation using Physical Model (DEPM) and Data Estimation using Statistical Model (DESM). DEPM estimates the values of sleeping nodes by the physical characteristics of sensed attributes, while DESM estimates the values through the spatial and temporal correlations of the nodes. Experimental results on real sensor networks show that the proposed techniques provide accurate estimations and conserve energy efficiently.

No abstract

No abstract

No abstract