Federated learning (FL) is a paradigm for training deep neural network (DNN) models on a distributed set of client devices without sharing local datasets. An FL server updates the global model by aggregating client models’ weights and transferring the updated model back to clients for future training rounds. One key aspect of FL is the disparity in data quality across distributed clients. As a result, the data used for model training on different devices is non-independent and identically distributed (non-IID) and suffers from quantity, label, and feature skewnesses. Data distribution and quality heterogeneities introduce biases that prevent the global model from achieving the desired convergence. Therefore, there is a need to select clients with relatively more balanced and better-quality data. This paper proposes I2Q-FL, a novel heuristic-based client selection mechanism for FL with heterogeneous data distribution. We formulate a metric called the IID-index that uses feature information and enables the FL server to rank the clients. Next, we propose a scheduling algorithm to engage clients in the model training process, ensuring the participation count is restricted within an upper bound. We conducted an extensive empirical study by implementing I2Q-FL ( https://github.com/PriyankaDas-16/I2Q-FL ) on an open-source FL evaluation platform called FedEval. We compared our approach with seven baselines, including the centralized model training approach on four publicly available and one real-life dataset for grayscale and RGB images. Experimental results demonstrate that I2Q-FL is scalable and achieves convergence in a reasonable time. It selects clients with balanced and better quality data, resulting in model accuracy marginally lower than the centralized approach, but outperforming the others. Except the centralized model, I2Q-FL outperforms all baseline by 4.1

The increasing frequency of natural disasters has heightened the demand for unmanned aerial vehicle (UAV) technologies. UAVs, especially drones, can monitor remote disaster areas and provide situational awareness to emergency responders. Equipped with cameras and onboard computers, drones can detect survivors in real-time, enhancing the efficiency of Search and Rescue (SAR) operations. Due to limited battery capacity, the drones must be deployed along a path of the shortest possible length to avoid delays in detecting the survivors in a given disaster area. Traditional path-planning algorithms struggle to address the dynamic conditions in disaster areas. We propose an adaptive drone path planning framework for real-time survivor detection in disaster areas to address this. This framework aims to improve survivor detection by guiding UAVs along routes with higher probabilities of the presence of survivors. Adopting a "Learn-As-You-Go" strategy, it trains a Potential Survivor Location (PSL) prediction model to identify way-points for drone sorties. Next, it leverages a novel computationally efficient path planning approach called Prediction-Based Priority-Aware Path Planning (PB-PAPP) to navigate towards the identified PSLs. Also, we present a Weight Synthesis module that enhances the prediction quality over time by aggregating the weights of the models trained by the drones, allowing continuous adaptation in changing environments. Finally, we present a prototype lightweight decentralized machine learning system that combines the above modules to facilitate real-time survivor detection. Compared to existing algorithms, our framework demonstrates an 84-97% reduction in overhead for adaptive path-planning.

QUIC (Quick UDP Internet Connection) is a transport layer protocol that allows the transfer of parallel and independent data streams. It does not involve a three-way handshake mechanism like TCP to establish a connection, but ensures fast and reliable in-order delivery. QUIC is faster than TCP but more secure and reliable than UDP, making it a preferred transport layer protocol for Internet-based real-time delay-sensitive applications, viz., online gaming, AR/VR, video streaming, etc. These applications mostly run atop IoT devices such as smartphones, wearables, and tablet computers. However, one security challenge persists in QUIC that may be exploited by adversaries. During the initial connection establishment handshake phase between a client and a server, the QUIC protocol does not encrypt the message, thus exposing the control parameters to man-in-the-middle (MITM) attacks. This work proposes a resource-friendly framework, eQUIC, that uses a modulo arithmetic-based cryptographic mechanism to secure the initial handshake phase. To efficiently manage cryptographic keys, the parameters necessary for the operations are maintained and dynamically refreshed at a trusted third-party Certificate Authority (CA). We perform experiments on a real testbed to demonstrate the efficacy of eQUIC in terms of CPU cycles, memory overhead, power consumption, and latency. To establish robustness against attacks, we test the proposed cryptographic scheme against a few common MITM attacks.

The Internet of Things (IoT) constitutes an ecosystem of 6LoWPAN networked resource-constrained devices that entail lightweight security solutions. Owing to the resource limitation of these devices and the delay-sensitive nature of applications running on them, an efficient authentication mechanism is required to validate requesters’ identities with minimum resources and delay. Inthis work, we adopted the Hessian curve, a variant of the elliptic curve and unexplored in Elliptic Curve Cryptography, to propose a distributed authentication mechanism called HessianAuth. Unlike other elliptic curves, it avoids using the expensive “point inversion” curve operation. We leveraged this property to generate digital signatures for authenticating device identities for low-power devices in IoT networks. We simulate a 6LoWPAN environment on the Contiki-based Cooja simulator and empirically show that our approach outperformed three baselines: AES-CBC, the standard Weierstrass curve-based ECC, and the Edward curve-based ECC regarding CPU usage, latency, and power consumption. Finally, we conduct a theoretical security analysis to deduce the validity of mutual authentication done by HessianAuth and its robustness to various identity theft attacks.

The transition of the web from centralized to decentralized or distributed architectures offers numerous advantages but also introduces significant challenges. One of the key challenges is user profiling to provide personalization, particularly personalized content recommendations. Traditional centralized recommendation systems rely on aggregated user data and central servers, making them incompatible with the principles of decentralization in Web 3.0. To bridge this gap, we propose D-RecSys, a decentralized recommendation framework specifically designed for Web 3.0-based content-sharing dApps. D-RecSys combines federated learning and clustering algorithms to deliver personalized recommendations while preserving user privacy and anonymity. The framework leverages blockchain technology for trustless coordination, enabling the generation of a global model through a modified block structure and mining algorithm. This structure facilitates the aggregation of local models into intermediate block models and subsequently produces the global model. To validate the effectiveness of D-RecSys, we conducted a number of experiments in a simulated Web 3.0 environment. To ensure the generalization capability of the framework, we used three datasets from different domains, i.e., anime recommendation, e-commerce product recommendation, and cellphone recommendation. The results demonstrate that D-RecSys achieves performance levels comparable to centralized recommendation systems while adhering to the core principles of decentralization, user anonymity, and data privacy.

QUIC (Quick UDP Internet Connections) is a relatively recent transport layer protocol that Google deployed and implemented for the first time in 2012. The key aspect of this protocol is that it is faster than TCP, more secure than UDP, and more efficient regarding resource usage. It has been adopted by some Internet-based applications, viz., YouTube, Gmail, etc. Recent advancements in 5G/6G communication technology have enabled the integration of QUIC with many real-time applications. One of the drawbacks in the design of the QUIC protocol is its vulnerability against attacks related to connection ID, and a recent attack of this type is the retire connection ID stuffing attack. This attack leads to a denial of service (DoS) condition, thus hindering network operations and services. Few preventive solutions have been proposed, but they focus on closing the connection after detecting an attack scenario, which results in service disruption. In this paper, we attempted to render flexibility to this rigid security defense mechanism situation by proposing iQUIC, an intelligent framework to configure a network condition monitoring QUIC server. The framework inputs the network data to a local Advantage Actor–Critic (A2C) Reinforcement Learning (RL) engine to support decision-making regarding accepting/rejecting a request from a client or issuing a warning signal to it. The framework also enables the server to stochastically suspend connections with the client(s) following in ϵ-greedy approach after a predefined observation window. To replicate a real-world QUIC-enabled network, we devised a small QUIC network consisting of two clients and a server and generated substantial QUIC traffic by implementing a U-Net-based GAN (Generative Adversarial Network) model from scratch. A simulation-based performance evaluation demonstrates that the QUIC server powered by the actor–critic RL learns to make optimal decisions with time.

Wireless Body Area Networks (WBANs) are pivotal in health care and wearable technologies, enabling seamless communication between miniature sensors and devices on or within the human body. These biosensors capture critical physiological parameters, ranging from body temperature and blood oxygen levels to real-time electrocardiogram readings. However, WBANs face significant challenges during and after deployment, including energy conservation, security, reliability, and failure vulnerability. Sensor nodes, which are often battery-operated, expend considerable energy during sensing and transmission due to inherent spatiotemporal patterns in biomedical data streams. This paper provides a comprehensive survey of data-driven approaches that address these challenges, focusing on device placement and routing, sampling rate calibration, and the application of machine learning (ML) and statistical learning techniques to enhance network performance. Additionally, we validate three existing models (statistical, ML, and coding-based models) using two real datasets, namely the MIMIC clinical database and biomarkers collected from six subjects with a prototype biosensing device developed by our team. Our findings offer insights into strategies for optimizing energy efficiency while ensuring security and reliability in WBANs. We conclude by outlining future directions to leverage approaches to meet the evolving demands of healthcare applications.

The pandemic caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has impacted the economy, health, and society. Emerging strains are making pandemic management challenging. There is an urge to collect epidemiological, clinical, and physiological data to make an informed decision on mitigation. Advances in the Internet of Things (IoT) and edge computing provide solutions for pandemic management through data collection and intelligent computation. While existing data-driven architectures operate on specific application domains and attempt to automate decision-making, they do not capture the multifaceted interaction among computational models, communication infrastructure, and data. In this article, we survey the existing approaches for pandemic management, including data repositories and contact-tracing applications. We envision a unified pandemic management architecture that leverages the IoT and edge computing paradigms to automate recommendations on vaccine distribution, dynamic lockdown, mobility scheduling, and pandemic trend prediction. We elucidate the data flow among the layers, namely, cloud, edge, and end device layers. Moreover, we address the privacy implications, threats, regulations, and solutions that may be adapted to optimize the utility of health data with security guarantees. The article ends with a discussion of the limitations of the architecture and research directions to enhance its practicality.

In areas affected by natural disasters, the functionality of communication networks is often compromised, resulting in partial or complete outages. Effective message sharing, crucial for facilitating prompt recovery efforts, is achieved by establishing mobile ad-hoc networks among user-owned devices. Network operations in post-disaster scenarios are inhibited by intermittent connectivity, delays, and energy constraints, necessitating routing strategies that ensure seamless communication amidst node failures and mobility challenges. To meet this challenge, we previously introduced an adaptive and distributed routing mechanism named ADRIN , capitalizing on the inherent periodicity in human mobility. The present work, ADRIN2.0 , extends the capabilities of ADRIN by incorporating a first-order Markov model-based mobility tracing approach to discern stable communication routes. It creates a spatiotemporal ad-hoc network to relay data multi-hop to the base station. Extensive simulations affirm that ADRIN2.0 approximates the underlying mobility distribution and facilitates data forwarding, even during node failures. ADRIN2.0 achieves a balance between data delivery rate and energy efficiency while minimizing latency, showing improvements over three centralized and two distributed routing benchmarks.

Data and communication networks in disaster-hit areas are often crippled due to partial or complete outages of the networking infrastructures. In such challenging post-disaster scenarios, message sharing is indispensable for a timely recovery. Typically, it is done by building mobile ad-hoc networks by devices in possession of users. However, challenged networks are often constrained by intermittent connectivity, delay, and energy constraints, necessitating routing strategies that offer seamless communication in the face of node failure and mobility. In this paper, we present an adaptive and distributed routing mechanism termed ADRIN. It employs backtracking-based mobility tracing, inspired by the backward algorithm of Hidden Markov Models, to infer periodicity in mobility to determine stable routes and then constructs a spatiotemporal ad-hoc network to relay data in a multi-hop fashion to the base station. Preliminary experiments show that ADRIN approximates the underlying mobility distribution and performs data forwarding despite failures.

Routing Protocol for Low Power and Lossy Networks (RPL) is the de-facto routing standard in IoT networks. It enables nodes to collaborate and autonomously build ad-hoc networks modeled by tree-like destination-oriented direct acyclic graphs (DODAG). Despite its widespread usage in industry and healthcare domains, RPL is susceptible to insider attacks. Although the state-of-the-art RPL ensures that only authenticated nodes participate in DODAG, such hard security measures are still inadequate to prevent insider threats. This entails a need to integrate soft security mechanisms to support decision-making. This paper proposes iTRPL, an intelligent and behavior-based framework that incorporates trust to segregate honest and malicious nodes within a DODAG. It also leverages multi-agent reinforcement learning (MARL) to make autonomous decisions concerning the DODAG. The framework enables a parent node to compute the trust for its child and decide if the latter can join the DODAG. It tracks the behavior of the child node, updates the trust, computes the rewards (or penalties), and shares them with the root. The root aggregates the rewards/penalties of all nodes, computes the overall return, and decides via its ϵ-Greedy MARL module if the DODAG will be retained or modified for the future. A simulation-based performance evaluation demonstrates that iTRPL learns to make optimal decisions with time.

The Tactile Internet paradigm is set to revolutionize human society by enabling skill-set delivery and haptic communication over ultra-reliable, low-latency networks. The emerging sixth-generation (6G) mobile communication systems are envisioned to underpin this Tactile Internet ecosystem at the network edge by providing ubiquitous global connectivity. However, apart from a multitude of opportunities of the Tactile Internet, security and privacy challenges emerge at the forefront. We believe that the recently standardized QUIC protocol, characterized by end-to-end encryption and reduced round-trip delay would serve as the backbone of Tactile Internet. In this article, we envision a futuristic scenario where a QUIC-enabled network uses the underlying 6G communication infrastructure to achieve the requirements for Tactile Internet. Interestingly this requires a deeper investigation of a wide range of security and privacy challenges in QUIC, that need to be mitigated for its adoption in Tactile Internet. Henceforth, this article reviews the existing security and privacy attacks in QUIC and their implication on users. Followed by that, we discuss state-of-the-art attack mitigation strategies and investigate some of their drawbacks with possible directions for future work

The increasing usage of the Internet of Things (IoT) across various domains has led to a significant surge in data generation and processing. This exponential growth has introduced numerous data security, privacy, integrity, and availability challenges. Blockchain has emerged as a promising technology to address these challenges. Nevertheless, the resource-constrained nature of IoT devices does not align well with the excessive resource requirements of traditional blockchain systems. While state-of-the-art research has mainly concentrated on making the blockchain lightweight in terms of computational overhead, the issue of managing the append-only, immutable, and ever-growing ledger remains largely unaddressed. In this paper, we propose a novel approach, termed FabMAN, to effectively manage the continuously expanding ledger in the context of Hyperledger Fabric, a permissioned blockchain platform widely adopted for blockchain-based IoT applications. We introduce an adaptive algorithm to dynamically adjust its “Batch size" and “Batch timeout to optimize its ledger growth." The adaptive algorithm ensures that the ledger growth is nearly optimal, considering the incoming transaction proposal rate. To validate the effectiveness and performance of the proposed method, we conduct comprehensive performance analyses through simulation and prototype implementation and compare the results with the same system model without the ledger management system. Our approach to managing the ever-growing ledger in Hyperledger Fabric-based IoT applications shows significant improvement.

The Internet of Things (IoT) paradigm has widespread applications across many fields in which private and sensitive user or environmental data are sensed and shared. Most present-day IoT applications depend on centralized cloud servers for authentication and access control. Validating the identity of a user and determining the legitimacy of his/her access requests require multiple rounds of data communications over the untrusted Internet, exposing sensitive data to potential attacks. Thus, protecting these data from security and privacy attacks and ensuring legitimate access is imperative. To address this challenge, we adopt an emerging technology called blockchain to propose a decentralized security framework called BloAC. It ensures secure access control in IoT networks without the intervention of the back-end cloud. We have used the Hyperledger Fabric, an open-source, permissioned blockchain platform, for implementing a prototype system using customized attribute-based access control (ABAC) policies. We have performed simulated and real test bed-based experiments to illustrate that BloAC outperforms the cloud server-based access control in latency and scalability. Finally, we conduct a security analysis to formally verify the ABAC policies used in BloAC and establish its robustness against attacks theoretically and using the AVISPA tool.

Traditional document verification processes suffer from inefficiencies due to their time-consuming nature and reliance on manual intervention, making them susceptible to errors. Moreover, verification of the same set of documents multiple times incurs costs for the document owners. Blockchain-based document verification frameworks have been proposed and are in practice to address some of the aforesaid challenges. However, most existing solutions rely on public blockchains, suitable for some use cases but pose privacy challenges in document verification environments where a closed and trusted ecosystem is essential. Furthermore, many of these solutions predominantly use the blockchain as an immutable data repository, overlooking its potential as a secure communication and data-sharing platform for the participants in document verification processes. Additionally, they focus on specific document types, such as identity documents or academic certificates, and lack generality. This paper presents a distributed document verification and sharing framework, called FabDVS, by leveraging an open-source permissioned blockchain platform called the Hyperledger Fabric. FabDVS envisions connecting various document issuing authorities, universities, recruiters, and so on to a private blockchain network and streamlining document sharing and verification processes while enhancing their speed and efficiency. The system ensures data integrity and confidentiality by inheriting the security, privacy, and role-based access control features of the Hyperledger Fabric and avoids repetitive verification of the same document. The performance analysis of the prototype implemented in a simulated environment shows that the delay in the verification process is minuscule and is thus convenient for real-time use cases.

Internet of Things (IoT) constitutes an ecosystem of networked resource-constrained devices that mandates light-weighted security solutions. In most IoT applications, co-located and proximal devices are connected in 6LoWPAN networks and use the IEEE 802.15 standard for local interactions via device-to-device (D2D) communication. The resource-limited 6LoWPAN networked devices need an efficient authentication mechanism to validate requesters' identities such that less resources and time are required. In this paper, we propose a novel Elliptic Curve Cryptography (ECC)-based distributed authentication scheme called HessianAuth to achieve efficiencies in resource usage and latency as well as security. We simulated a 6LoWPAN network to support a D2D communication scenario and implemented the proposed authentication mechanism using the Cooja network simulator. We have considered AES-CBC and standard Weierstrass curve-based ECC as the benchmarks and carried out performance analysis with respect to CPU cycles and delay. Further, we carry out a security analysis of HessianAuth using a state-of-the-art tool called AVISPA and demonstrate that the former is secure against man-in-the-middle and replay attacks.

Mobile wireless sensor networks (MWSNs) have the ability of sensing and reporting a variety of environmental phenomena without human presence under potentially adverse conditions, making them indispensable for safety, research, military, and surveillance applications. In addition to the energy and communication challenges of wireless sensor networks, the Quality of Service (QoS) of MWSNs continues to be hampered by abrupt changes in topology. This paper addresses this challenge by exploiting the notion of "periodicity", defined as the tendency of mobile nodes to periodically visit zones (termed waypoints). To this end, we first discuss the use of supervised machine learning to learn and update the mobility patterns of nodes from temporal mobility traces, and then use periodicity to arrive upon a holistic spatio-temporal view of the dynamically evolving mobile WSN that can overcome the uncertainty of changing topology. We design a customized discrete event platform that uses the public transport dataset of 20 waypoints in Rome, Italy to validate the proposed approach. Using Support Vector Machine and Routing protocol for Low-Power and Lossy Networks (RPL) as representative supervised machine learning and routing approaches, respectively, the paper shows that periodicity-based routing improves QoS.

Internet of Things (IoT) enables the collection of large volumes of data by billions of pervasive intelligent devices and sharing them with remote cloud servers for processing, resulting in increasing network congestion and server response times. The advent of edge computing has addressed these challenges by introducing an intermediate edge layer comprising networked fog nodes that provide on-demand computation, caching, and communication services to meet critical Quality-of-Service (QoS) requirements. However, in a challenging environment brought by disaster and aftershocks, the QoS is hampered as several fog nodes in the edge layer are damaged. Nevertheless, the existing network infrastructure should still support the uninterrupted flow of time-critical contextual data between the survivors and rescuers for quick recovery operations. In this work, we envision that the IoT devices and existing fog nodes will collaborate to form ad-hoc networks for emergency message delivery under disaster situations. We present a distributed routing mechanism, termed motif centrality-based routing ( $MCR$ ), that leverages the concept of network motifs (subgraphs) seen in social and biological networks. Specifically, the proposed mechanism addresses three QoS requirements of an ad-hoc network: 1) robustness against component failures; 2) low latency; and 3) energy efficiency. We experimentally show that the $MCR$ -based routing ensures high data delivery, low latency, and comparable efficiency in energy usage. Finally, an extensive simulation-based study shows that $MCR$ outperforms the related benchmarks in terms of the three QoS requirements.

Software Defined Wireless Sensor Networks (SD-WSN) is a promising paradigm in wireless communication that offers high flexibility in network management by enabling dynamic and programmable network control. SDN controller has a centralized global view of the network, making it an ideal choice for data sensing in a highly dynamic sensing environment. We proposed a reinforcement learning (RL) based adaptive topology control approach (Roy et al., IEEE CCNC 2020) that employs periodic node mobility to meet diverse network objectives, such as data delivery, latency, and energy efficiency. We also demonstrated that erratic mobility can considerably hamper the learning of the RL module resulting in poor overall quality of service. In this work, we present a customized network simulation environment that captures the variations in the performance of the proposed SD-WSN framework. Finally, we present a new approach based on supervised machine learning that can identify periodic mobility and mitigate the ill-effects of erratic mobility.

Wireless Sensor Networks (WSNs) enable promising solutions to large-scale industrial, medical and environmental tracking and monitoring applications. Software Defined Networking (SDN) is a new paradigm that decouples the network control and data forwarding functionalities and may potentially improve data sensing in a highly dynamic environment. The networking community is directing its efforts towards ensuring that the software defined WSNs (SD-WSN) carry out the data sensing even in a hostile environment characterized by node or link failures. In this work, we present an adaptive topology control strategy based on reinforcement learning for mobile SD-WSN. The approach employs the notion of statistically significant subgraphs, called motifs, that have been shown to render graph robustness to biological networks. Our simulation experiments on the map of New York City shows that this approach is capable of modulating network parameters to achieve varying goals such as high data delivery, low latency and energy efficiency.