TermID: a distributed swarm intelligence-based approach for wireless intrusion detection

Abstract

With the mushrooming of wireless access infrastructures, the amount of data generated, transferred and consumed by the users of such networks has taken enormous proportions. This fact further complicates the task of network intrusion detection, especially when advanced machine learning (ML) operations are involved in the process. In wireless environments, the monitored data are naturally distributed among the numerous sensor nodes of the system. Therefore, the analysis of data must either happen in a central location after first collecting it from the sensors or locally through collaboration by viewing the problem through a distributed ML perspective. In both cases, concerns are risen regarding the requirements of this demanding task in matters of required network resources and achieved security/privacy. This paper proposes TermID, a distributed network intrusion detection system that is well suited for wireless networks. The system is based on classification rule induction and swarm intelligence principles to achieve efficient model training for intrusion detection purposes, without exchanging sensitive data. An additional achievement is that the produced model is easily readable by humans. While these are the main design principles of our approach, the accuracy of the produced model is not compromised by the distribution of the tasks B Constantinos Kolias and remains at competitive levels. Both the aforementioned claims are verified by the results of detailed experiments withheld with the use of a publicly available security-focused wireless dataset.

Deep Abstraction and Weighted Feature Selection for Wi-Fi Impersonation Detection

“…Bostani et al [17] proposed an anomaly-based IDS by modifying an optimum path forest combined with k-means clustering. A distributed anomaly-based IDS, called T ermID, proposed by Kolias et al [18] incorporating ant colony optimization and rule induction in a reduced data operation to achieve data parallelism and reduce privacy risks.…”

An efficient deep learning model for intrusion classification and prediction in 5G and IoT networks

“…For a given training dataset X = {x 1 , x 2 , ..., x m } with m samples or instances, where x n is an n-dimensional feature vector, the encoder maps the input vector x n to a hidden representation vector h n through a deterministic mapping f θ as given in (2)…”

“…Any hacks in banking systems, healthcare systems and many Internet of Things (IoT) devices could cause huge monetary losses every year and loss of services at crucial times. This drove to an increase in research for more secured online systems specifically in the intrusion detection systems [2]- [4]. With the majority of internet traffic occurring over wireless networks, and the domain is constantly updating with 5G and IoT technologies, there are likely many gaps in the security of these networks that can be exploited through intrusion attempts.…”

Evaluating Security of Low-Power Internet of Things Networks

“…They analysed a set of well-know algorithms to detect threats on an IoT network. [42] proposed TermID which is a distributed network for intrusion detection system based on classification rule and swarm intelligence principles to detect an attack on execution on the network. [43] also compared a serious of machine learning and algorithms to detect threats on 802.11 protocol.…”