Journal of Cybersecurity and Information Management

Big data has become an integral part of modern businesses, but its management and protection present numerous challenges, such as securing sensitive information from unauthorized access, preventing data breaches, and ensuring data integrity. This work investigated applying a machine learning (ML) approach to tackling the challenges of information security and management in big data environments. We present an ML framework that leverages a supervised learning strategy to detect anomalies, classify big data, and predict potential security threats. We also investigate the implementation of this framework and its potential benefits, such as reducing false positives and improving detection rates. Our experimental analysis in public datasets demonstrates the effectiveness of our approach in improving information security and management in big data environments.

Mathematical programming can express competency concepts in a well-defined mathematical model for a particular Any system that runs is always be expected to experience faults in  different ways. Any change in the physical state of numerous components, control machinery, as well as environmental factors, might result in these problems. In process industries, where prompt detection is crucial in maintaining high product quality, dependability, and safety under various operating situations, finding these flaws is one of the most difficult tasks. The goal of this project is to implement several machine learning techniques for fault identification and classification in a binary distillation column. A pilot binary distillation unit (UOP3CC) is utilized for this purpose. The set up is run under normal operating conditions and the real time data is collected. Three common faults namely reboiler fault, feed pump fault and sensor fault are introduced one at a time and the faulty data is collected. These data are then introduced in to different machine learning algorithms like Logistic Regression, KNN, Naive Bayes, Decision Tree, Gradient Boosting, X Gradient Boosting, SVC and Light Gradient Boosting for model development. 70% of the data samples used for training and 30% of data samples are used for testing. It is found the Decision tree algorithm gives the best accuracy possible with 99.9%. Using decision tree algorithm, fault classification is performed for different datasets and is found that the algorithm was able to classify accurately even for new untrained datasets.

The proliferation of Internet of Things (IoT) devices has led to an increase in the number of malware attacks targeting these devices. Traditional security mechanisms such as firewalls and antivirus software are often inadequate in protecting IoT devices from malware attacks due to their limited resources and the heterogeneity of IoT networks. In this paper, we propose DeepSecureIoT, a deep learning-based framework for securing IoT against malware attacks. Our proposed framework uses a deep convolutional neural network (CNN) to extract features from network traffic and classify it as normal or malicious. The CNN is trained using a large dataset of network traffic to accurately identify malware attacks and reduce false positives. We evaluate the performance of DeepSecureIoT using a benchmark dataset of real-world IoT malware attacks. The results show that our proposed framework achieves an accuracy of 0.961 in detecting and classifying malware attacks, outperforming state-of-the-art intrusion detection systems. Moreover, DeepSecureIoT has low computational overhead and can be deployed on resource-constrained IoT devices.

The advent of the Internet of Things (IoT) has led to the proliferation of connected devices, creating numerous security challenges. With billions of devices generating vast amounts of data, managing information security risks in the age of IoT has become increasingly complex. Traditional security approaches are not sufficient to mitigate the risks posed by IoT devices. Machine learning (ML) provides a promising approach to enhance the security of IoT systems. This paper proposes a machine learning approach for managing information security risks in the age of IoT. The proposed approach utilizes ML algorithms to identify and mitigate security threats in IoT systems. The approach involves collecting and analyzing data from IoT devices, and applying ML algorithms to detect patterns and anomalies that may indicate security threats. The ML algorithms are trained using both supervised and unsupervised learning techniques to enable them to identify known and unknown threats. The paper describes a case study in which the proposed approach is applied to an IoT system for home security. The results demonstrate that the ML approach can effectively detect security threats in the IoT system and mitigate them in real-time.

Cloud computing has become a popular paradigm for delivering computing resources and services over the internet. However, the adoption of cloud computing also brings new security challenges and risks, including data breaches, insider attacks, and unauthorized access. Therefore, it is critical to have a comprehensive information security management framework to address these challenges and ensure the security and privacy of cloud computing environments. This paper proposes a machine learning (ML) based information security management (ISM) framework for cloud computing environments that integrates best practices and standards from various domains, including cloud computing, information security, and risk management. The proposed framework includes residual recurrent network to effectively discriminate different patterns of cloud security attacks. The proposed framework emphasizes the importance of threat detection, security controls, and continuous monitoring and improvement. The framework is designed to be flexible and scalable, allowing organizations to tailor it to their specific needs and requirements.

Applications that are enabled by blockchain technology have been infused with a decentralized system without the need for intermediate entities. Blockchain technology indicates opportunities with various technologies and applications.  Recently, a meteoric rise in the amount of interest has been indicated by academics in blockchain technology. Nevertheless, the acceptance of this blockchain technology paradigm in corporate distributed systems is not exactly promising. Executives and technocrats in a business are required to engage in multiple-criteria decision-making (MCDM) with operating uncertainty factors for the acceptance of new technologies. The proposed model aims to develop a model to identify and keep track of major elements that contribute to the sluggish pace for blockchain technology to be adopted by the general public. The study applied the Evaluation Based on the Distance from Average Solution (EDAS) approach to its interval-valued neutrosophic variant, which has the benefit of concurrently with the consideration of a decision maker's truthiness, falsity, and indeterminacy. The EDAS considers the distances of alternatives from the actual solutions considered by each criterion. In addition, the proposed model illustrated the use of neutrosophic theory with the EDAS method to rank blockchain technology in enterprise-distributed applications in uncertain conditions to aid decision-makers in optimal solutions. A numerical case study is illustrated to show the effectiveness of the proposed model in aiding decision-makers to achieve optimal solutions in uncertain conditions.