With the advancement of Internet technologies Cyber attacks have become a significant risk to overall security, therefore, intelligent security systems are required to strengthen the network security against these threats. Machine learning has played a pivotal role in the detection and mitigation of these attacks over the years. However, to identify the zero-day attacks and incorporate frequently changing attack scenarios, techniques need to be developed that can work with minimally labeled data. In this paper, we propose Time aware LSTM Autoencoder-based learning approach to detect the attack in network flows by training the model using only normal traffic and using reconstruction error as the parameter to classify the attack event. We perform the experiments on different recent datasets like CICDDoS2019, & CICIDS2018 and experimental results exhibit that the proposed model overall provides better classification metrics.
Paper
Full text
Network based Intrusion Detection using Time aware LSTM Autoencoder
Semantic Scholar · Computer Science · 2023
Abstract
With the advancement of Internet technologies Cyber attacks have become a significant risk to overall security, therefore, intelligent security systems are required to strengthen the network security against these threats. Machine learning has played a pivotal role in the detection and mitigation of these attacks over the years. However, to identify the zero-day attacks and incorporate frequently changing attack scenarios, techniques need to be developed that can work with minimally labeled data. In this paper, we propose Time aware LSTM Autoencoder-based learning approach to detect the attack in network flows by training the model using only normal traffic and using reconstruction error as the parameter to classify the attack event. We perform the experiments on different recent datasets like CICDDoS2019, & CICIDS2018 and experimental results exhibit that the proposed model overall provides better classification metrics.