A Novel Jamming Attacks Detection Approach Based on Machine Learning for Wireless Communication

Abstract

Jamming attacks target a wireless network creating an unwanted denial of service. 5G is vulnerable to these attacks despite its resilience prompted by the use of millimeter wave bands. Over the last decade, several types of jamming detection techniques have been proposed, including fuzzy logic, game theory, channel surfing, and time series. Most of these techniques are inefficient in detecting smart jammers. Thus, there is a great need for efficient and fast jamming detection techniques with high accuracy. In this paper, we compare the efficiency of several machine learning models in detecting jamming signals. We investigated the types of signal features that identify jamming signals, and generated a large dataset using these parameters. Using this dataset, the machine learning algorithms were trained, evaluated, and tested. These algorithms are random forest, support vector machine, and neural network. The performance of these algorithms was evaluated and compared using the probability of detection, probability of false alarm, probability of miss detection, and accuracy. The simulation results show that jamming detection based random forest algorithm can detect jammers with a high accuracy, high detection probability and low probability of false alarm.

Lightweight Hybrid Deep Learning Architecture and Model for Security in IIOT

“…As a result, the initial step in maintaining security and privacy is to determine the vulnerabilities being faced. The authors of [12] suggested a zone partitioning-based anomaly detection mechanism for industrial cyber-physical systems based on the creation of a zonal functional model. Intrusion responses for industrial control systems were proposed by researchers in [13].…”

“…Following are the types of attacks such as backdoor, analysis, reconnaissance, exploit, generic, fuzzer, DoS, worm, and shellcode assaults. The authors in [12] identify the network size of a packet, IP addresses of both source and destination, ports, set of rules, and so on, that can be used to forecast harmful malicious activity. The UNSW-NB15 dataset is used in the cited paper to train and test their model.…”

JADE: Data-Driven Automated Jammer Detection Framework for Operational Mobile Networks

“…A straightforward approach to jammer detection is to treat it as a supervised binary classification problem. In fact, most recent works on jammer detection [18]- [22], though aimed at 802.11 networks, take this approach, and show Random Forests (RF) [23] to be the most effective classifier. Here we assess the effectiveness of supervised binary classification approach towards jammer detection in operational mobile networks, considering RF as the classifier.…”

Extreme Communication in 6G: Vision and Challenges for ‘in-X’ Subnetworks

“…Several techniques can be used for jamming detection, mostly at the physical layer, based on pilot/data transmission and pseudorandom blanking of frequency, time or spatial resources [93]. Moreover, AI with both unsupervised [94] and supervised learning, e.g., in the form of support vector machine, random forest and neural network [95], can be used to improve the detection capabilities of classical statistical signal processing algorithms and heuristics. It can also help in better characterizing the jammer strategies, thus allowing for specific mitigation countermeasures.…”