Abstract
Currently, expert systems and applied machine learning algorithms are widely used to automate network intrusion detection. In critical infrastructure applications of communication technologies, the interaction among various industrial control systems and the Internet environment intrinsic to the IoT technology makes them susceptible to cyber-attacks. Given the existence of the enormous network traffic in critical Cyber-Physical Systems (CPSs), traditional methods of machine learning implemented in network anomaly detection are inefficient. Therefore, recently developed machine learning techniques, with the emphasis on deep learning, are finding their successful implementations in the detection and classification of anomalies at both the network and host levels. This paper presents an ensemble method that leverages deep models such as the Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and a meta-classifier (i.e., logistic regression) following the principle of stacked generalization. To enhance the capabilities of the proposed approach, the method utilizes a two-step process for the apprehension of network anomalies. In the first stage, data pre-processing, a Deep Sparse AutoEncoder (DSAE) is employed for the feature engineering problem. In the second phase, a stacking ensemble learning approach is utilized for classification. The efficiency of the method disclosed in this work is tested on heterogeneous datasets, including data gathered in the IoT environment, namely IoT-23, LITNET-2020, and NetML-2020. The results of the evaluation of the proposed approach are discussed. Statistical significance is tested and compared to the state-of-the-art approaches in network anomaly detection.
Highlights
Critical structures such as Internet Industrial Control Systems (ICS) and Sensitive Industrial Plants and Sites (SIPS) need to be functional and operate reliably even when subjected to unforeseen threats or external attacks
Selection of the latest network traffic datasets featuring labeled network flows and corresponding features to evaluate the proposed approach; developing a suitable model that integrates the key features in the feature engineering phase to facilitate the design architectures that resist, at least to some extent, certain types of deliberate attempts to evade detection or, more generally, subvert the protection offered by the proposed method; the design of the deep models integrated by the stacked generalization method, which is generated by a group of selected models followed by a meta-classifier that learns the best way of facilitating the synergy of a group of models
This work addressed an ensemble approach incorporating deep learning algorithms using the concept of stacked generalization for an effective anomaly-based network intrusion detection system
Summary
Critical structures such as Internet Industrial Control Systems (ICS) and Sensitive Industrial Plants and Sites (SIPS) need to be functional and operate reliably even when subjected to unforeseen threats or external attacks. The main goal of a malicious user is to get access to one of these layers to steal or tamper with sensitive data This is doable physically, remotely, or through a combined vector of attack. Some of the contemporary solutions use a correlation engine with the Kafka architecture that performs effective anomaly-based intrusion detection for streaming data in the application layer This kind of system adopts the lambda architecture featuring the scalable data processing framework named Apache Kafka, which facilitates an engine that processes Big Data workloads. The key aspects of this kind of design enable a distributed computing system that integrates multiple machine learning and deep learning models This particular example facilitates an application module that offers different intrusion detection tools and a visualization module for the end-users
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.