The growing number of security threats has prompted the use of a variety of security techniques. The most common security tools for identifying and tracking intruders across diverse network domains are intrusion detection systems. Machine Learning classifiers have begun to be used in the detection of threats, thus increasing the intrusion detection systems’ performance. In this paper, the investigation model for an intrusion detection systems model based on the Principal Component Analysis feature selection technique and a different Support Vector Machine kernels classifier is present. The impact of various kernel functions used in Support Vector Machines, namely linear, polynomial, Gaussian radial basis function, and Sigmoid, is investigated. The performance of the investigation model is measured in terms of detection accuracy, True Positive, True Negative, Precision, Sensitivity, and F-measure to choose an appropriate kernel function for the Support Vector Machine. The investigation model was examined and evaluated using the KDD Cup’99 and UNSW-NB15 datasets. The obtained results prove that the Gaussian radial basis function kernel is superior to the linear, polynomial, and sigmoid kernels in both used datasets. Obtained accuracy, Sensitivity, and, F-measure of the Gaussian radial basis function kernel for KDD CUP’99 were 99.11%, 98.97%, and 99.03%. for UNSW-NB15 datasets were 93.94%, 93.23%, and 94.44%.

Most current research on decentralized IoT applications focuses on a specific vulnerability. However, for IoT applications, only a limited number of techniques are dedicated to handling privacy and trust concerns. To address that, blockchain-based solutions that improve the quality of IoT networks are becoming increasingly used. In the context of IoT security, a blockchain-based authentication framework could be used to store and verify the identities of devices in a decentralized manner, allowing them to communicate with each other and with external systems in a secure and trust-less manner. The main issues in the existing blockchain-based IoT system are the complexity and storage overhead. To solve these research issues, we have proposed a unique approach for a massive IoT system based on a permissions-based blockchain that provides data storage optimization and a lightweight authentication mechanism to the users. The proposed method can provide a solution to most of the applications which rely on blockchain technology, especially in assisting with scalability and optimized storage. Additionally, for the first time, we have integrated homomorphic encryption to encrypt the IoT data at the user’s end and upload it to the cloud. The proposed method is compared with other benchmark frameworks based on extensive simulation results. Our research contributes by designing a novel IoT approach based on a trust-aware security approach that increases security and privacy while connecting outstanding IoT services.

The Chat Generative Pre-training Transformer (GPT), also known as ChatGPT, is a powerful generative AI model that can simulate human-like dialogues across a variety of domains. However, this popularity has attracted the attention of malicious actors who exploit ChatGPT to launch cyberattacks. This paper examines the tactics that adversaries use to leverage ChatGPT in a variety of cyberattacks. Attackers pose as regular users and manipulate ChatGPT’s vulnerability to malicious interactions, particularly in the context of cyber assault. The paper presents illustrative examples of cyberattacks that are possible with ChatGPT and discusses the realm of ChatGPT-fueled cybersecurity threats. The paper also investigates the extent of user awareness of the relationship between ChatGPT and cyberattacks. A survey of 253 participants was conducted, and their responses were measured on a three-point Likert scale. The results provide a comprehensive understanding of how ChatGPT can be used to improve business processes and identify areas for improvement. Over 80% of the participants agreed that cyber criminals use ChatGPT for malicious purposes. This finding underscores the importance of improving the security of this novel model. Organizations must take steps to protect their computational infrastructure. This analysis also highlights opportunities for streamlining processes, improving service quality, and increasing efficiency. Finally, the paper provides recommendations for using ChatGPT in a secure manner, outlining ways to mitigate potential cyberattacks and strengthen defenses against adversaries.

In light of the increasing sophistication and frequency of mobile attacks, there is a growing demand for advanced intelligent techniques capable of offering comprehensive mobile attack detection and prevention. This paper aims to critically evaluate the landscape of mobile security, outlining the evolution of mobile attack vectors and pinpointing the deficiencies in traditional security methods. The text embarks on a journey to understand the connection between machine learning (ML) and its promising applications in enhancing mobile security. First, we outline the current state of mobile attacks and the traditional methods used for their detection, emphasizing the clear limitations and the necessity for an innovative approach. Following this, we will elucidate the fundamentals of ML and its implications in cybersecurity, exploring the benefits it can provide to mobile attack detection frameworks. We delve into discussing various ML algorithms, such as decision trees, random forests, and support vector machines, highlighting their effectiveness and the metrics used to evaluate ML models in security tasks. Moreover, the paper sheds light on novel approaches such as semi-supervised and unsupervised learning in anomaly detection, as well as the applications of transfer learning in security. Addressing the pressing challenges faced in artificial intelligence (AI)-driven mobile attack detection, we delve deep into the intricacies of data collection, labeling, and the prevailing issues of imbalance and overfitting. Furthermore, we explore contemporary adversarial attacks and defenses, scrutinizing the real-world adaptability of AI models and the pivotal role of human-AI collaboration in enhancing attack detection mechanisms.

The increasing sophistication and frequency of cyber threats necessitate the development of advanced techniques for detecting and mitigating attacks. This paper introduces a novel cybersecurity-focused Multi-Layer Perceptron (MLP) trainer that utilizes evolutionary computation methods, specifically tailored to improve the training process of neural networks in the cybersecurity domain. The proposed trainer dynamically optimizes the MLP’s weights and biases, enhancing its accuracy and robustness in defending against various attack vectors. To evaluate its effectiveness, the trainer was tested on five widely recognized security-related datasets: NSL-KDD, CICIDS2017, UNSW-NB15, Bot-IoT, and CSE-CIC-IDS2018. Its performance was compared with several state-of-the-art optimization algorithms, including Cybersecurity Chimp, CPO, ROA, WOA, MFO, WSO, SHIO, ZOA, DOA, and HHO. The results demonstrated that the proposed trainer consistently outperformed the other algorithms, achieving the lowest Mean Square Error (MSE) and highest classification accuracy across all datasets. Notably, the trainer reached a classification rate of 99.5% on the Bot-IoT dataset and 98.8% on the CSE-CIC-IDS2018 dataset, underscoring its effectiveness in detecting and classifying diverse cyber threats.

This paper presents a novel hybrid optimization algorithm that combines JADE Adaptive Differential Evolution with Artificial Protozoa Optimizer (APO) to solve complex optimization problems and detect attacks. The proposed Hybrid APO-JADE Algorithm leverages JADE’s adaptive exploration capabilities and APO’s intensive exploitation strategies, ensuring a robust search process that balances global and local optimization. Initially, the algorithm employs JADE’s mutation and crossover operations, guided by adaptive control parameters, to explore the search space and prevent premature convergence. As the optimization progresses, a dynamic transition to the APO mechanism is implemented, where Levy flights and adaptive change factors are utilized to refine the best solutions identified during the exploration phase. This integration of exploration and exploitation phases enhances the algorithm’s ability to converge to high-quality solutions efficiently. The performance of the APO-JADE was verified via experimental simulations and compared with state-of-the-art algorithms using the 2022 IEEE Congress on Evolutionary Computation benchmark (CEC) 2022 and 2021. Results indicate that APO-JADE achieved outperforming results compared with the other algorithms. Considering practicality, the proposed APO-JADE was used to solve a real-world application in attack detection and tested on DS2OS, UNSW-NB15, and ToNIoT datasets, demonstrating its robust performance.