Search

The file attached to this record is the author's final peer reviewed version. In this paper, we propose a federated learning-based intrusion detection system, named FELIDS, for securing agricultural-IoT infrastructures. Specifically, the FELIDS system protects data privacy through local learning, where devices benefit from the knowledge of their peers by sharing only updates from their model with an aggregation server that produces an improved detection model. In order to prevent Agricultural IoTs attacks, the FELIDS system employs three deep learning classifiers, namely, deep neural networks, convolutional neural networks, and recurrent neural networks. We study the performance of the proposed IDS on three different sources, including, CSE-CIC-IDS2018, MQTTset, and InSDN. The results demonstrate that the FELIDS system outperforms the classic/centralized versions of machine learning (non-federated learning) in protecting the privacy of IoT devices data and achieves the highest accuracy in detecting attacks.

In this paper, we present a comprehensive survey of privacy-preserving schemes for smart grid communications. Specifically, we select and in-detail examine thirty-two privacy preserving schemes developed for or applied in the context of smart grids. Based on both communication and system models, we classify these schemes that are published between 2013 and 2017, in five categories, including, (1) smart grid with advanced metering infrastructure, (2) data aggregation, (3) smart grid marketing architecture, (4) smart community of home gateways, and (5) vehicle-to grid architecture. For each scheme, we survey attacks of leaking privacy, countermeasures, and game theoretic approaches. In addition, we review survey articles published in the recent years that deal with smart grids communications, applications, standardization, and security. Based on the current survey, several recommendations for further research are discussed at the end of this paper.

The file attached to this record is the author's final peer reviewed version. The concept of the Internet of Vehicles (IoV) has attracted the attention of many sectors such as the automotive industry, academia, engineering, etc., offering a wide variety of benefits, such as reduced congestion, safer driving, and less pollution. However, since the deployment of IoT based devices is in an open field, the IoV environments can be a vital issue in the absence of security protections. In this paper, we propose an efficient authentication scheme over blockchain, named EASBF, for secure fog computing-enabled internet of vehicles. Specifically, the proposed EASBF scheme consists of five phases: initialization, registration, mutual authentication, and exchanging keys, consensus, and certificate update. Based on the elliptic curve cryptography, one-way hash function, and blockchain technology, the EASBF scheme can achieve confidentiality, integrity, authenticity, privacy, anonymity, non-repudiation, and perfect forward secrecy. The EASBF scheme is robust against cyber attacks, including, DDoS attack, replay attack, man-in-the-middle attacks, identity theft attack, traffic analysis attack, masquerading attack, and session key disclosure attack. Both the AVISPA tool and the random oracle model are used in security analysis. Finally, we demonstrate the effectiveness of the EASBF scheme in terms of two performance metrics, namely, computation overhead, communication overhead, and storage overhead.

Vehicular Ad-hoc Networks (VANETs), which are a subclass of Mobile Ad-hoc Networks (MANETs), received a widespread attention during the last decades. With these promising set of safety applications, which are the main reason why they were developed, VANETs are considered as a tremendous support for the Intelligent Transportation Systems (ITS). However, several key issues remain to be solved before VANET becomes fully applicable; one of them being privacy preservation. To fulfill safety-requirements in VANETs, the vehicle needs to broadcast its status wirelessly. Consequently, any adversary can hear the broadcast messages at the aim of analyzing them, identifying, tracking and generating profile of his target. In other words, privacy of individuals may be seriously breached in VANETs if no safety measures were been taken. Using pseudonyms instead of the real identities of individuals, and changing them periodically during the communication is a promising solution for such crucial problems. There is a significant body of research work addressing this issue and a lot of researchers proposed various privacy protections basing on pseudonym change strategies. In this survey paper, we present an introduction to the privacy problem and give a recent and detailed state of the art of the different suggested pseudonym change strategies and approaches. We also propose a novel taxonomy to classify these strategies to diverse concepts. Finally, we discuss, give future directions and open issues and mention some of the observations that lead to better identify this problem for better future strategies.