In recent years, all real-world processes have been shifted to the cyber environment practically, and computers communicate with one another over the Internet. As a result, there is a rising number of network security vulnerabilities, and network administrators are unable to secure their networks from all forms of cyberattacks. Many techniques for network intrusion detection have also been developed. However, they encounter significant challenges as a result of the ongoing emergence of new vulnerabilities that present systems cannot comprehend. We are motivated by deep learnings exceptional performance in various detection and identification tasks, we present an intelligent and efficient network intrusion detection system (NIDS) based on Deep Learning (DL). In this study, we present a deep learning-based IDS for attack detection. The model has been trained with real-time traffic datasets; CICIDS2018 and Edge_IIoT datasets. The performance of the model is investigated using multiclass classification and achieved a 100% and 99.64% accuracy rate respectively when trained and tested with the datasets.
Machine learning and deep learning techniques are widely used to assess intrusion detection systems (IDS) capable of rapidly and automatically recognizing and classifying cyber-attacks on networks and hosts. However, when destructive attacks are becoming more extensive, more challenges develop, needing a comprehensive response. Numerous intrusion detection datasets are publicly accessible for further analysis by the cybersecurity research community. However, no previous research has examined the performance of the proposed model on a variety of publicly accessible datasets in detail. Due to the dynamic nature of the attack and its rapidly changing attack techniques, the publicly accessible intrusion datasets must be updated and benchmarked regularly. The deep neural network (DNN) and convolutional neural network (CNN) are examined in this article as types of deep learning models for developing a flexible and effective IDS capable of detecting and comparing them with the proposed model in detecting cyber-attacks. The constant development of network behavior and the fast growth of attacks need the development of IDS and the evaluation of many datasets produced over time through static and dynamic methods. This kind of research enables the identification of the most efficient algorithm for identifying future cyber-attacks. We proposed a novel two-stage deep learning technique hybridizing Long-Short Term Memory (LSTM) and Auto-Encoders (AE) for detecting attacks. The CICIDS2017 and CSE-CICDIS2018 datasets are used to determine the optimum network parameters for the proposed LSTM-AE. The experimental results show that the proposed hybrid model works well and is applicable for detecting attacks in modern scenarios.
Intrusion detection systems (IDS) play a critical role in safeguarding computer networks against unauthorized access and malicious activities. However, traditional IDS approaches face challenges in accurately detecting complex and evolving cyber threats. The proposed framework leverages the power of deep learning to automatically extract meaningful features from network traffic data, enabling more accurate and robust intrusion detection. The proposed deep convolutional neural network (DCNN) has been trained on large-scale datasets, incorporating both normal and malicious network traffic, to enable effective discrimination between normal and anomalous behavior. To evaluate the performance of the framework, a comprehensive performance evaluation approach is developed, considering key metrics such as detection accuracy, false positive rate, and computational efficiency. Additionally, GPU has been utilized for boosting the performance of the model, demonstrating the effectiveness and superiority of the deep CNN-based intrusion detection system over traditional methods. The novelty of this study lies in the development of a dependable intrusion detection system that harnesses the potential of DCNN for network traffic analysis. The proposed framework is evaluated with four publicly available IDS datasets, namely ISCX-IDS 2012, DDoS (Kaggle), CICIDS2017, and CICIDS2018. Our results demonstrate the effectiveness of the optimized DCNN model in improving IDS performance and accuracy. With detection accuracy levels ranging from 99.79% to 100%, our results underscore the model’s efficacy, offering a dependable and efficient approach for the detection of cyber threats. The outcomes of this study have significant implications for network security, providing valuable insights for practitioners and researchers working towards building robust and intelligent intrusion detection systems.
6 March 2024 in Telematics and Informatics Reports