A Study: Machine Learning and Deep Learning Approaches for Intrusion Detection System

Sekhar, Ch.; Rao, K. Venkata

doi:10.1007/978-3-030-37051-0_94

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The behavioral features focus on network traffic characteristics, such as source-destination ports/IP addresses, various packets-level/flow-level statistics, and duration of collections. Various deep neural networks were developed in recent literatures to evaluate the network behaviors [23][24][25][26][27][28][29][30][31][32] . In the contrast, content features are used to uncover patterns of intrusions through the content of payloads in the traffic.…”

Section: Related Workmentioning

confidence: 99%

Applying big data based deep learning system to intrusion detection

Zhong

2020

Big Data Min. Anal.

113

View full text Add to dashboard Cite

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.

show abstract