Intrusion detection systems (IDSs) play a pivotal role in computer security by discovering and repealing malicious activities in computer networks. Anomaly-based IDS, in particular, rely on classification models trained using historical data to discover such malicious activities. In this paper, an improved IDS based on hybrid feature selection and two-level classifier ensembles are proposed. A hybrid feature selection technique comprising three methods, i.e., particle swarm optimization, ant colony algorithm, and genetic algorithm, is utilized to reduce the feature size of the training datasets (NSL-KDD and UNSW-NB15 are considered in this paper). Features are selected based on the classification performance of a reduced error pruning tree (REPT) classifier. Then, a two-level classifier ensemble based on two meta learners, i.e., rotation forest and bagging, is proposed. On the NSL-KDD dataset, the proposed classifier shows 85.8% accuracy, 86.8% sensitivity, and 88.0% detection rate, which remarkably outperform other classification techniques recently proposed in the literature. The results regarding the UNSW-NB15 dataset also improve the ones achieved by several state-of-the-art techniques. Finally, to verify the results, a two-step statistical significance test is conducted. This is not usually considered by the IDS research thus far and, therefore, adds value to the experimental results achieved by the proposed classifier.INDEX TERMS Two-stage meta classifier, network anomaly detection, hybrid feature selection, intrusion detection system, statistical significance test.

No abstract

Internet of Things (IoT)-based devices, especially those used for home automation, consist of their own sensors and generate many logs during a process. Enterprises producing IoT devices convert these log data into more useful data through secondary processing; thus, they require data from the device users. Recently, a platform for data sharing has been developed because the demand for IoT data increases. Several IoT data marketplaces are based on peer-to-peer (P2P) networks, and in this type of marketplace, it is difficult for an enterprise to trust a data owner or the data they want to trade. Therefore, in this study, we propose a review system that can confirm the reputation of a data owner or the data traded in the P2P data marketplace. The traditional server-client review systems have many drawbacks, such as security vulnerability or server administrator’s malicious behavior. However, the review system developed in this study is based on Ethereum smart contracts; thus, this system is running on the P2P network and is more flexible for the network problem. Moreover, the integrity and immutability of the registered reviews are assured because of the blockchain public ledger. In addition, a certain amount of gas is essential for all functions to be processed by Ethereum transactions. Accordingly, we tested and analyzed the performance of our proposed model in terms of gas required.

No abstract

The personal health information (PHI) is an activity among the health-care providers and the patients in terms of managing the data which is sensitive to the parties. The PHI data have been maintained by multiple health-care providers, thus resulting in separated data. Moreover, the PHI data are stored in the provider's database, hence the patients have no authority to manage their own information. Therefore, in this article, we propose a conceptual model for managing the PHI data which is derived from several health-care providers by relying on the blockchain technology in the peer-to-peer overlay network. In addition, we elaborate the security analysis that might be occurring in the proposed model. By leveraging on our model, it allows the patients and the providers to collect effectively the PHI data onto a single view as well guarantee of data integrity. The blockchain offers an immutable of the data record without having to trust a third party. The experimental results show that the proposed approach is promising to be developed due to the high success rate in terms of data dissemination.