Detection of Real-Time Malicious Intrusions and Attacks in IoT Empowered Cybersecurity Infrastructures

Abstract

Computer viruses, malicious, and other hostile attacks can affect a computer network. Intrusion detection is a key component of network security as an active defence technology. Traditional intrusion detection systems struggle with issues like poor accuracy, ineffective detection, a high percentage of false positives, and an inability to handle new types 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 learning-based discriminative approaches. This paper presents a generative adversarial network to detect cyber threats in IoT-driven IICs networks. The results demonstrate a performance increase of approximately 95% to 97% in terms of accuracy, reliability, and efficiency in detecting all types of attacks with a dropout value of 0.2 and an epoch value of 25. 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: (BruteForceXXS, BruteForceWEB, DoS_Hulk_Attack, and DOS_LOIC_HTTP_Attack) on the 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.

An Application of the Khumbelo Function on the Camellia Algorithm to Prevent Attacks in IoT Devices

“…Encryption is unavoidable in all layers of IoT. The network layer is responsible for denial of service (DoS) attacks, ransomware attacks, botnets, sniers, and unauthorized access [10]. According to recent research, more than 98% of trac sent by IoT devices is unencrypted, exposing vast amounts of personal and condential data to potential attackers [10].…”

“…The DoS attack is an intrusion that consumes various resources and service oerings of the company by spreading unusable trac and preventing dependable users from using the services [10]. DoS attackers generally maintain their independence by working with multiple victim machines and monitoring legitimate network trafc, making detection more dicult [10]. Network trac should be encrypted with a robust algorithm to prevent DoS, and access control should be implemented with a robust hash authentication algorithm [10].…”

“…DoS attackers generally maintain their independence by working with multiple victim machines and monitoring legitimate network trafc, making detection more dicult [10]. Network trac should be encrypted with a robust algorithm to prevent DoS, and access control should be implemented with a robust hash authentication algorithm [10].…”

“…More ransomware gangs penetrate networks via the network layer to encrypt all data stored in servers, enduser, and other IoT devices [10]. Ransomware intruders encrypt and steal data from storage and require a lot of money from data owners to decrypt data, including selling the stolen data to the owner's adversaries.…”

“…Ransomware intruders encrypt and steal data from storage and require a lot of money from data owners to decrypt data, including selling the stolen data to the owner's adversaries. Prevention of ransomware attacks should be that all data in the storage should be encrypted using a strong encryption algorithm and stored in external storage where the network layer is not used [10].…”