• Non-Interactive Zero Knowledge Proofs for the Authentication of IoT Devices in Reduced Connectivity Environments

      Epiphaniou, Gregory; Walshe, Marcus; Al-Khateeb, Haider; Hammoudeh, Mohammad; Katos, Vasilios; Dehghantanha, Ali (Elsevier, 2019-08-21)
      Current authentication protocols seek to establish authenticated sessions over insecure channels while maintaining a small footprint considering the energy consumption and computational overheads. Traditional authentication schemes must store a form of authentication data on the devices, putting this data at risk. Approaches based on purely public/private key infrastructure come with additional computation and maintenance costs. This work proposes a novel noninteractive zero knowledge (NIZKP) authentication protocol that incorporates the limiting factors in IoT communication devices and sensors. Our protocol considers the inherent network instability and replaces the ZKP NP-hard problem using the Merkle tree structure for the creation of the authentication challenge. A series of simulations evaluate the performance of NIZKP against traditional ZKP approaches based on graph isomorphism. A set of performance metrics has been used, namely the channel rounds for client authentication, effects of the authentication processes, and the protocol interactions to determine areas of improvements. The simulation results indicate empirical evidence for the suitability of our NIKP approach for authentication purposes in resourceconstrained IoT environments.
    • Robust Deep Identification using ECG and Multimodal Biometrics forIndustrial Internet of Things

      Alkeem, Ebrahim Al; Yeob Yeun, Chan; Yun, Jaewoong; Yoo, Paul D; Chae, Myungsu; Rahman, Arafatur; Asyhari, A Taufiq (Elsevier, 2021-06-12)
      The use of electrocardiogram (ECG) data for personal identification in Industrial Internet of Things can achieve near-perfect accuracy in an ideal condition. However, real-life ECG data are often exposed to various types of noises and interferences. A reliable and enhanced identification method could be achieved by employing additional features from other biometric sources. This work, thus, proposes a novel robust and reliable identification technique grounded on multimodal biometrics, which utilizes deep learning to combine fingerprint, ECG and facial image data, particularly useful for identification and gender classification purposes. The multimodal approach allows the model to deal with a range of input domains removing the requirement of independent training on each modality, and inter-domain correlation can improve the model generalization capability on these tasks. In multitask learning, losses from one task help to regularize others, thus, leading to better overall performances. The proposed approach merges the embedding of multimodality by using feature-level and score level fusions. To the best of our understanding, the key concepts presented herein is a pioneering work combining multimodality, multitasking and different fusion methods. The proposed model achieves a better generalization on the benchmark dataset used while the feature-level fusion outperforms other fusion methods. The proposed model is validated on noisy and incomplete data with missing modalities and the analyses on the experimental results are provided.
    • SPY-BOT: machine learning-enabled post filtering for social network-integrated industrial internet of things

      Rahman, Md Arafatur; Zaman, Nafees; Asyhari, A Taufiq; Sadat, SM Nazmus; Pillai, Prashant; Arshah, Ruzaini Abdullah (Elsevier, 2021-07-09)
      A far-reaching expansion of advanced information technology enables ease and seamless communications over online social networks, which have been a de facto premium correspondents in the current cyber world. The ever-growing social network data has gained attention in recent years and can be handy for industrial revolution 4.0. With the integration of social networks with the Internet of Things being noticed in different industries to enhance human involvement and increase their productivity, security in such networks is increasingly alarming. Vulnerabilities can be characterized in the form of privacy invasion, leading to hazardous contents, which can be detrimental to social media actors and in turn impact the processes of the overall Social Network-Integrated Industrial Internet of Things (SN-IIoT) ecosystem. Despite this prevalence, the current platforms do not have any significant level of functionality to capture, process, and reveal unhealthy content among the social media actors. To address those challenges by detecting hazardous contents and create a stable social internet environment within IIoT, a statistical learning-enabled trustworthy analytic tool for human behaviors has been developed in this paper. More specifically, this paper proposes a machine learning (ML)-enabled scheme SPY-BOT, which incorporates a hybrid data extraction algorithm to perform post-filtering that arbitrates the users’ behavior polarity. The scheme creates class labels based on the featured keywords from the decision user and classifies suspicious contacts through the aid of ML. The results suggest the potential of the proposed approach to classify the users’ behavior in SN-IIoT.