The global aging population poses an urgent challenge in ensuring the safety and well-being of elderly individuals. With the rapid development of technologies such as the Internet of Medical Things (IoMT), new avenues for digital healthcare services (DHS) offer promising solutions to support elder-care safety. Simultaneously, society stands at the threshold of a transformative era characterized by the immersive and interconnected 3D landscape of the Metaverse, reshaping how people live, work, and socialize. While fully realizing a comprehensive digital Metaverse landscape remains a vision with various challenges and open questions, a lightweight metaverse version is within reach. This paper proposes an innovative Fuzzy Neural Network (FNN) enhanced Image-based Action Recognition (FIAR) system in Microverse — an edge-scale IoMT Metaverse designed for DHS. Utilizing adaptive FNNs, FIAR enhances the adaptability of the multi-sensor fusion process to accommodate varying input modes and quantities of input sources to reduce decision uncertainty and learn fuzzy relationships among multiple data streams. An experimental study confirms the feasibility of the Microverse framework and FIAR’s capacity to deliver accurate and rapid responses, validating its effectiveness in safeguarding independently living elderly individuals.

Federated Learning (FL) has been recognized as a privacy-preserving machine learning (ML) technology that enables collaborative training and learning of a global ML model based on the aggregation of distributed local model updates. However, security and privacy guarantees could be compromised due to malicious participants and the centralized aggregation manner. Possessing attractive features like decentralization, immutability and auditability, Blockchain is promising to enable a tamper-proof and trust-free framework to enhance performance and security in IoT based FL systems. However, directly integrating blockchains into the large scale IoT-based FL scenarios still faces many limitations, such as high computation and storage demands, low transactions throughput, poor scalability and challenges in privacy preservation. This paper proposes uDFL, a novel hierarchical IoT network fabric for decentralized federated learning (DFL) atop of a lightweight blockchain called microchain. Following the hierarchical infrastructure of FL, participants in uDFL are fragmented into multiple small scale microchains. Each microchain network relies on a hybrid Proof of Credit (PoC) block generation and Voting-based Chain Finality (VCF) consensus protocol to ensure efficiency and privacy-preservation at the network of edge. Meanwhile, microchains are federated vie a high-level inter-chain network, which adopts an efficient Byzantine Fault Tolerance (BFT) consensus protocol to achieve scalability and security. A proof-of-concept prototype is implemented, and the experimental results verify the feasibility of the proposed uDFL solution in cross-devices FL settings with efficiency, security and privacy guarantees.

The prevalence of Internet of Things (IoT) allows heterogeneous and lightweight smart devices to collaboratively provide services with or without human intervention. With an ever-increasing presence of IoT-based smart applications and their ubiquitous visibility from the Internet, user data generated by highly connected smart IoT devices also incur more concerns on security and privacy. While a lot of efforts are reported to develop lightweight information assurance approaches that are affordable to resource-constrained IoT devices, there is not sufficient attention paid from the aspect of security solutions against hardware-oriented attacks, i.e. side channel attacks. In this paper, a COTS (commercial off-the-shelf) based Randomized Switched-Mode Voltage Regulation System (RSMVRS) is proposed to prevent power analysis based side channel attacks (P-SCA) on bare metal IoT edge device. The RSMVRS is implemented to direct power to IoT edge devices. The power is supplied to the target device by randomly activating power stages with random time delays. Therefore, the cryptography algorithm executing on the IoT device will not correlate to a predictable power profile, if an adversary performs a SCA by measuring the power traces. The RSMVRS leverages COTS components and experimental study has verified the correctness and effectiveness of the proposed solution.

As smart surveillance becomes popular in today’s smart cities, millions of closed circuit television (CCTV) cameras are ubiquitously deployed that collect huge amount of visual information. All these raw visual data are often transported over a public network to distant video analytic centers. This increases the risk of interception and the spill of individuals’ information into the wider cyberspace that causes privacy breaches. The edge computing paradigm allows the enforcement of privacy protection mechanisms at the point where the video frames are created. Nonetheless, existing cryptographic schemes are computationally unaffordable at the resource constrained network edge. Based on chaotic methods we propose three lightweight end-to-end (E2E) privacy-protection mechanisms: (1) a Dynamic Chaotic Image Enciphering (DyCIE) scheme that can run in real time at the edge; (2) a lightweight Regions of Interest (RoI) Masking (RoI-Mask) scheme that ensures the privacy of sensitive attributes on video frames; and (3) a novel lightweight Sinusoidal Chaotic Map (SCM) as a robust and efficient solution for enciphering frames at edge cameras. Design rationales are discussed and extensive experimental analyses substantiate the feasibility and security of the proposed schemes.