Abstract
The current rise in hacking and computer network attacks throughout the world has heightened the demand for improved intrusion detection and prevention solutions. The intrusion detection system (IDS) is critical in identifying abnormalities and assaults on the network, which have grown in size and pervasiveness. The paper proposes a novel approach for network intrusion detection using multistage deep learning image recognition. The network features are transformed into four-channel (Red, Green, Blue, and Alpha) images. The images then are used for classification to train and test the pre-trained deep learning model ResNet50. The proposed approach is evaluated using two publicly available benchmark datasets, UNSW-NB15 and BOUN Ddos. On the UNSW-NB15 dataset, the proposed approach achieves 99.8% accuracy in the detection of the generic attack. On the BOUN DDos dataset, the suggested approach achieves 99.7% accuracy in the detection of the DDos attack and 99.7% accuracy in the detection of the normal traffic.
Highlights
Cyberattacks and cybersecurity risks have skyrocketed in new technologies such as cloud computing, fog computing, edge computing, and the Internet of Things (IoT)
For handling and analyzing very large volumes of data in real time, the framework [14] used a distributed deep learning model with DNNs that was chosen after a thorough evaluation of its performance against traditional machine learning classifiers on publicly available network-based intrusion datasets such as KDDCup 99, NSL-KDD, Kyoto, UNSW-NB15, WSN-DS, and CICIDS
Based on the empirical results presented in Sections 4.2.1 and 4.2.2, we consider that the precision of image classification on the testing dataset when the ML.NET model was created on the UNSW-NB15 training dataset may be distributed and the detection process would require two stages
Summary
Cyberattacks and cybersecurity risks have skyrocketed in new technologies such as cloud computing, fog computing, edge computing, and the Internet of Things (IoT). The deep learning model identifies network attacks on its own using a measurable property of a network traffic feature (NTF) that is being observed Because of their great efficiency and ease of implementation, DL models have steadily been applied to intrusion detection to improve classification classifiers in recent years. Various data pre-processing approaches are used to supply machine learning techniques with adequate NTF record values in order to extract and prepare informative features from these datasets for the classification module. The detailed experimental analysis of the proposed pre-processing approach for the deep learning training process using transfer learning for network intrusion detection performed on the classification of various network attack types with UNSW-NB15 and BOUN DDoS datasets;.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
