ML-Based Delay Attack Detection and Isolation for Fault-Tolerant Software-Defined Industrial Networks

Abstract

Traditional security mechanisms find difficulties in dealing with intelligent assaults in cyber-physical systems (CPSs) despite modern information and communication technologies. Furthermore, resource consumption in software-defined networks (SDNs) in industrial organizations is usually on a larger scale, and the present routing algorithms fail to address this issue. In this paper, we present a real-time delay attack detection and isolation scheme for fault-tolerant software-defined industrial networks. The primary goal of the delay attack is to lower the resilience of our previously proposed scheme, SDN-resilience manager (SDN-RM). The attacker compromises the OpenFlow switch and launches an attack by delaying the link layer discovery protocol (LLDP) packets. As a result, the performance of SDN-RM is degraded and the success rate decreases significantly. In this work, we developed a machine learning (ML)-based attack detection and isolation mechanism, which extends our previous work, SDN-RM. Predicting and labeling malicious switches in an SDN-enabled network is a challenge that can be successfully addressed by integrating ML with network resilience solutions. Therefore, we propose a delay-based attack detection and isolation scheme (DA-DIS), which avoids malicious switches from entering the routes by combining an ML mechanism along with a route-handoff mechanism. DA-DIS increases network resilience by increasing success rate and network throughput.

Smart Preventive Maintenance of Hybrid Networks and IoT Systems Using Software Sensing and Future State Prediction

“…When complex systems, including more networks and subsystems, are to be monitored, different approaches include dedicated sensors, IoT platforms, and a LSTM ensemble neural, which are all developed to predict the operational status [31], and for avoiding cascading failures, a hybridization of two meta-heuristic techniques, namely, the snake optimizer and the sine-cosine algorithm (SO-SCA), are proposed to solve the problem [32]. A fault-tolerant topology algorithm for agricultural WSN, based on a double-price function, is designed in [33] to improve the connectivity and reliability of the WSN, while some approaches employ a trained multi-agent for comparing the computed future state with the actual state and early detect faults [34].…”

Identifying Fake Digital Information Using Machine Learning Algorithms: Performance Analysis and Recommendation System

“…The features are then extracted using a ResNExt CNN, a RNN with LSTM, and by recording the GAN-induced temporal discrepancies between frames. It uploaded and classified videos using a webbased platform; the primary purpose was to assess performance, security, user friendliness, correctness, and reliability [52][53][54].…”

Development of Fingerprint Identification Based on Device Flow in Industrial Control System

“…The high economic rewards of attacking industrial systems have led to the rapid development of attack methods, so effective and resilient anomaly detection solutions are needed to deal with evolving attack methods [1]. However, it is difficult for network administrators to manage industrial control systems in terms of security, network resources, and device troubleshooting unless they can identify the devices connected to the industrial control network [2].…”