The enormous growth of the Internet and its usage creates many vulnerabilities, so network anomaly detection becomes a crucial problem these days. With this tremendous growth of the internet applications makes the security is a top priority for everyone. An attack might cause loss of valuable information/assets to any individual or the organization, attacker may be insider or outsider of the organization. The challenging part is to identify the attack real-time and act accordingly to prevent the losses, either in the form of data or money. In the early age of the network intrusion detection systems (NIDS) statistical and data mining techniques are used to detect the intrusions. These techniques have the limitations, these approach can’t perform well with the huge data. Deep learning approaches performance increases with the data size. These techniques can predict the occurrence of the attack more accurately. With the availability of huge processing capability and enormous network data deep learning algorithms are become more flexible in detection of these anomalies accurately. In this work, the recurrent neural network algorithm and its variants are used to detect the network anomalies.
CITATION STYLE
Ravinder Reddy, R., Ayyappa Reddy, K., Madan Kumar, C., & Ramadevi, Y. (2021). Detection of Network Anomaly Sequences Using Deep Recurrent Neural Networks. In Smart Innovation, Systems and Technologies (Vol. 224, pp. 605–615). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-1502-3_60
Mendeley helps you to discover research relevant for your work.