Due to the extensive use of computer networks, new risks have arisen, and improving the speed and accuracy of security mechanisms has become a critical need. Although new security tools have been developed, the fast growth of malicious activities continues to be a pressing issue that creates severe threats to network security. Classical security tools such as firewalls are used as a first-line defense against security problems. However, firewalls do not entirely or perfectly eliminate intrusions. Thus, network administrators rely heavily on intrusion detection systems (IDSs) to detect such network intrusion activities. Machine learning (ML) is a practical approach to intrusion detection that, based on data, learns how to differentiate between abnormal and regular traffic. This paper provides a comprehensive analysis of some existing ML classifiers for identifying intrusions in network traffic. It also produces a new reliable dataset called GTCS (Game Theory and Cyber Security) that matches real-world criteria and can be used to assess the performance of the ML classifiers in a detailed experimental evaluation. Finally, the paper proposes an ensemble and adaptive classifier model composed of multiple classifiers with different learning paradigms to address the issue of the accuracy and false alarm rate in IDSs. Our classifiers show high precision and recall rates and use a comprehensive set of features compared to previous work.
Security and privacy are among the key barriers to adopting the Internet of Medical Things (IoMT) solutions. IoMT adopters have to adhere to security and privacy policies to ensure that patient data remains confidential and secure. However, there is confusion among IoMT stakeholders as to what security measures they should expect from the IoMT manufacturers and whether these measures would comply with the adopter's security and compliance requirements. In this paper, we present a recommendation tool that models IoMT concepts and security issues in addition to successively recommending security measures. The presented tool utilizes semantically enriched ontology to model the IoMT components, security issues, and measures. The developed ontology is equipped with context-aware rules to enable reasoning in order to build a recommendation system that empowers users to make well-educated decisions. The recommendation tool classifies IoMT security threats faced by IoMT stakeholders and automatically recommends security controls that have to be enforced for each threat. We have experimented the proposed tool with respect to the completeness and effectiveness of its output (i.e., security issues and recommended security measures). The results show that the tool was effectively able to recommend necessary security measures.
Fog computing is an intermediate computing layer that has emerged to address the latency issues of cloud-based Internet of things (IoT) environments. As a result, new forms of security and privacy threats are emerging. These threats are mainly due to the huge number of sensors, as well as the enormous amount of data generated in IoT environments that needs to be processed in real time. These sensors send data to the cloud through the fog computing layer, creating an additional layer of vulnerabilities. In addition, the cloud by nature is vulnerable because cloud services can be located in different geographical locations and provided by multiple service providers. Moreover, cloud services can be hybrid and public, which exposes them to risks due to their infinite number of anonymous users. Access control (AC) is one of the essential prevention measures to protect data and services in computing environments. Many AC models have been implemented by researchers from academia and industry to address the problems associated with data breaches in pervasive computing environments. However, the question of which AC model(s) should be used to prevent unauthorized access to data remains. The selection of AC models for cloud-based IoT environments is highly dependent on the application requirements and how the AC models can impact the computation overhead. In this paper, we survey the features and challenges of AC models in the fog computing environment. We also discuss the diversity of different AC models. This survey provides the reader with state-of-the-art practices in the field of fog computing AC and helps to identify the existing gaps within the field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.