Network Intrusion Detection Systems (NIDS) are designed to safeguard the security needs of enterprise networks against cyber-attacks. However, NIDS networks suffer from several limitations, such as generating a high volume of low-quality alerts. Moreover, 99% of the alerts produced by NIDSs are false positives. As well, the prediction of future actions of an attacker is one of the most important goals here. The study has reviewed the state-of-the-art cyber-attack prediction based on NIDS Intrusion Alert, its models, and limitations. The taxonomy of intrusion alert correlation (AC) is introduced, which includes similarity-based, statistical-based, knowledge-based, and hybrid-based approaches. Moreover, the classification of alert correlation components was also introduced. Alert Correlation Datasets and future research directions are highlighted. The AC receives raw alerts to identify the association between different alerts, linking each alert to its related contextual information and predicting a forthcoming alert/attack. It provides a timely, concise, and high-level view of the network security situation. This review can serve as a benchmark for researchers and industries for Network Intrusion Detection Systems’ future progress and development.
The Internet of Things (IoT) has grown into various enterprise. While the IoT ecosystem's extensive and open environment has many advantages, it can also be a target for a range of growing cyber risks and assaults. The benefits of device integration into a smart ecosystem are enhanced by the IoT's diversity, but the IoT's diverse nature makes establishing a single security solution difficult. However, software-defined networks' (SDNs) centralized intelligence and programmability, it's now possible to put together a single, effective security solution to combat cyber threats and attacks. This study proposes a DL-driven SDN-enabled IoT framework that practice a Deep Neural Network-Long Short-Term Memory (LSTM) classifier to quickly and efficiently detect sophisticated multisector malware botnets. The proposed mechanism was rigorously tested utilizing the most recent state-of-the-art dataset, CICIDS2017, as well as traditional performance evaluation metrics. Furthermore, the proposed technique is compared to current industry norms (i.e., DL algorithms). Extensive testing shows that the proposed method surpasses the competition in terms of detection accuracy while requiring just a minimal compromise in terms of computational cost.