Trustworthy transmission is a beneficial step towards the success of new era of telecommunication technologies and Online Social Networks (OSNs). Many sensitive applications can benefit from OSNs, e.g., eHealth and medical services. However, OSNs have always been prey to Sybil attacks where numerous fake nodes are being generated and propagated in social networks to mimic like real nodes for the purpose of achieving malicious goals. Thus, for security reasons and for the sensitivity of data used in eHealth applications, such fake nodes have to be detected and deactivated immediately. The emerging field of Internet of Medical Things (IoMT) promotes trust management among various IoMT devices to provide accurate and reliable communications, which is quite essential in critical diseases such as COVID-19. Trust Management (TM) provides a secure platform to IoMT devices using different security protocols in the IoMT network. Generically, if a device is not comfortable to connect with additional devices in a network, the motive of communication process is not succeeded and leads to disappointment for one device toward others. To handle these types of situations, a trust management mechanism, named Fuzzy-based Trust Management Mechanism for preventing Sybil Attacks in the Internet of Medical Things (FTM-IoMT), is proposed. The FTM-IoMT provides trust management for the users of eHealth systems using IoMT infrastructures. It is an intelligent mechanism to recognize sybil or untrustworthy nodes in the system. The proposed mechanism helps IoMT nodes to collect authentic and credible information from their neighboring nodes as well as to neglect sybil nodes. The trust value of a node is evaluated using fuzzy logic processing followed by the trust attributes, such as integrity, receptivity, and compatibility of a node. The FTM-IoMT provides double evaluation check based on fuzzy logic processing and fuzzy filter. The proposed scheme shows superior results when compared to the state-of-the-art approaches.

In this paper, we propose H-IDFS, a Histogram-based Intrusion Detection and Filtering framework, which assembles the CAN packets into windows, and computes their corresponding histograms. The latter are fed to a multi-class IDS classifier to identify the class of the traffic windows. If the window is found malicious, the filtering system is invoked to filter out the normal CAN packets from each malicious window. To this end, we propose a novel one-class SVM, named OCSVM-attack that is trained on normal traffic and considers the invariant and quasi-invariant features of the attack. Experimental results on two CAN datasets: OTIDS and Car-Hacking, show the superiority of the proposed H-IDFS, as it achieves an accuracy of 100% for window classification, and correctly filters out between 94.93% and 100% of normal packets from malicious windows.

Internet of Medical Things (IoMT) provides a diverse platform for healthcare to enhance the accuracy, reliability, and efficiency. In addition, it utilizes the productivity of available equipment to improve patients’ health. IoMT also provides distinct ways by which healthcare will be revolutionized as it provides numerous opportunities to handle operations with precision. However, numerous advantages have raised several security challenges, such as trust, data integrity, network constraints, and real-time processing among others. There is a requirement for a robust approach to maintain data integrity along with the behavior detection of nodes to completely maintain a secure environment. In the proposed approach, the mechanism is capable of maintaining a robust network by predicting and eliminating malicious nodes. The proposed NeuroTrust approach utilizes the trust parameters to evaluate the degree of trust that include reliability, compatibility, and packet delivery. This approach also lightens the two-way computation burden and uses a lightweight encryption mechanism to further enhance the security and integrity during data dissemination, which is required for the digital revolution in delivering efficient high quality healthcare. The performance of the proposed approach has been extensively evaluated against the absolute trust formulation, accuracy of trust computation, energy consumption, and several potential attacks. The simulation results show the effective performance to identify malicious and compromised nodes, and maintain resilience against various attacks.

In Vehicular Ad-hoc Networks (VANET), vehicles act like mobile nodes for fetching, sharing, and disseminating important information related to vehicle safety, warning messages, emergency events, and passenger infotainment. Due to continuous information sharing of vehicles with their surrounding nodes, Road Side Units (RSUs), and infrastructures, the existing host-centric IP-based network cannot fulfill the requirements of VANETs. Therefore, Information Centric Networking (ICN) architectures are the introduced to comprehensively address the problems of Internet of Things (IoT)-based VANETs, known as VANET-IoT. This paper introduces a new ICN-based proactive left-right-front (LRF) caching strategy for VANETs, which maximizes the performance of VANETs by placing content proactively at the right nodes. The proposed strategy also provides a mechanism for the timely dissemination of safety-related messages. LRF is compared with other caching strategies in the NS-3 simulator, which outperforms those schemes in terms of cache utilization, hop ratios, and resolved interest ratios with respect to 100 MB, 500 MB, and 1 GB cache sizes.

Forecasting crowd congestion is a critical aspect of crowd management, particularly in dynamic and densely populated areas, such as urban centers, events, or pilgrimage sites. In this paper, we proposed the first crowd congestion forecasting framework for the pilgrimage of Umrah. We addressed the crowd congestion forecasting problem by clustering the crowd flow trajectory in Masjid Al-Haram (Great Mosque) in the city of Makkah into six zones. The framework consists of two main components: 1) Ensemble forecasting model that aims at forecasting the crowd density of Masjid Al-Haram and its six zones, and 2) decision making algorithm that aims at keeping the crowd density at an acceptable level, and recommends updating the crowd flows when the forecasted crowd density exceeds the crowd density threshold. We built the ensemble learning model in three phases. In the first phase, we selected and evaluated different learning base models, including ARIMA, Sequence to Sequence (Seq2Seq) learning, M-1D-CNN-LSTM, and DeepSTN. In the second phase, the best three models, which performed well in the first phase, are selected to build the stacked ensemble model. The latter is validated using the walk-forward technique in the third phase. To evaluate the framework, we built a crowd dataset based on two temporal properties: 1) hourly context and 2) daily context. We evaluated the three phases of the ensemble forecasting model. In the first phase, DeepSTN performs the best by achieving a Mean Absolute Error (MAE) of 0.281. The results also indicate that DeepSTN is the best fit for five zones, and one variant of Seq2Seq, named Seq2Seq2b is the best fit for one zone under Mean Square Error (MSE) and Root Mean Squared Error (RMSE). Under MAE, DeepSTN and Seq2Seq2b, each of which is the best choice for three zones. In the second phase, the stacked ensemble achieves a MAE of 0.257. In the third phase, the stacked ensemble model is validated using the walk forward technique, which allows to reduce the MAE to 0.253. Although this framework focuses on Umrah, it can be customized for other use cases that involve crowd congestion forecasting.