Proactive Identification of Live Cyber Threats in IoT-Enhanced Security Systems

A computer network may be impacted by malicious software, computer viruses, and other hostile attacks. A crucial element of network security is intrusion detection, which is an active defensive system. Traditional intrusion detection systems suffer from problems including poor accuracy, poor detection, a high rate of false positives, and an inability to handle novel forms of intrusions. To address these issues, we propose a deep learning-based novel method to detect cybersecurity vulnerabilities and breaches in cyber-physical systems. The proposed framework contrasts the unsupervised and deep learningbased discriminative approaches. We presents a generative adversarial network to detect cyber threats in IoT-driven IICs networks. The results demonstrate a performance increase in terms of accuracy, reliability, and efficiency in detecting all types of attacks. The output of well-known state-of-the-art DL classifiers achieved the highest true rate (TNR) and highest detection rate (HDR) when detecting the following attacks such as BruteForceXXS, BruteForceWEB, DoS_Hulk_Attack, and DOS_LOIC_HTTP_Attack on the three data sets namely NSL-KDD, KDDCup99, and UNSW-NB15 datasets. It also maintained the confidentiality and integrity of users’ and systems’ sensitive information during the training and testing phases