Ensure Data Privacy Research Articles

Federated learning‐based privacy‐preserving electricity load forecasting scheme in edge computing scenario

SummaryIn the era of big data, massive amounts of data hold great value. However, much data exists as isolated islands, and the maximum value of the data cannot be fully utilized. Federated learning allows each client to train local data and then share the training model parameters securely, which can address the isolated data island problem and exploit data value while ensuring data privacy and security. Accordingly, in order to securely complete the electric power load forecasting using existing data, this paper constructs a federated learning‐based privacy‐preserving scheme to support electricity load forecasting in edge computing scenarios. To address the problems of the data‐isolated islands and data privacy in electric power systems, this paper proposes a decentralized distributed solution based on the federated learning technique. Our scheme achieves electricity load forecasting for power systems through the federated learning‐based framework and uses edge computing architecture to improve real‐time data capability and reduce network latency. For the hierarchical scheduling structure in power systems, we divide the system into a cloud‐side‐device three‐layer architecture, which achieves structural coordination and balance, and each layer collects information according to the scheduling control tasks, promoting scheduling effectiveness. Finally, different privacy protection methods are used on the cloud‐edge and edge‐device sides to significantly enhance data security. Moreover, We have conducted extensive experimental simulations for our proposed scheme. The experimental results show that the relative error of electricity load forecasting is around 1.580%. Meanwhile, our scheme achieves high accuracy and low memory usage. The security analysis proves the feasibility and security of our scheme.

Selection of a viable blockchain service provider for data management within the internet of medical things: An MCDM approach to Indian healthcare

Health 4.0 is gaining significant attention globally to support better treatment and care for people. Digital technologies such as the IoMT “(”Internet of Medical Things“”) and blockchain substantially promote quality health services. Literature shows that embedding blockchain in IoMT is an effective way to attain secure and quality healthcare. Selecting a viable blockchain service provider (BSP) becomes a complex task and can be considered an MCDM “(”Multi-Criteria Decision-Making“”) problem. Earlier studies on BSP selection indicate that complex expressions cannot be well-modelled and methodical estimation of decision parameters by capturing hesitation and interaction of entities is not adequately explored. Driven by the issues, authors put forward a novel MCDM framework with (i) a double hierarchy linguistic structure for data collection in natural expressions; (ii) regret measure for experts' reliability calculation; (iii) a weighted CRITIC approach for criteria weight determination, and (iv) CRADIS-Copeland algorithm for ranking BSPs. Finally, a case example from Recent Indian healthcare is exemplified to demonstrate the framework's applicability. Recently, the Indian healthcare sector launched initiatives/plans as part of Health 4.0 to promote data management for a better quality of treatment by seeking support from digital technologies such as IoMT and blockchains to ensure data privacy and improved customer experience. Sensitivity analysis and comparison with extant methods infer that (i) BC1, BC5, and BC3 are the top three BSPs for the considered problem; (ii) criteria such as privacy aspects, intercommunication capability, global accessibility, and total cost constitute 58% importance in the supposed decision problem; (iii) developed model reduces human intervention/biases; (iv) developed model is robust to weight alteration and yields unique rank orders with both personalised and cumulative ordering of BSPs; and (v) proposed model produces broader rank values that aid in effective backup planning.

A digital twin-based motion forecasting framework for preemptive risk monitoring

Risk monitoring is a critical task in numerous industrial fields, including construction engineering. Existing approaches primarily focus on identifying the immediate incidents of unsafe events, often neglecting the latent risks arising from the high uncertainty of agents’ motions. To bridge this gap and lay the basis for preemptive risk monitoring, this paper proposes a novel and effective digital twin-based motion forecasting framework that leverages cloud-edge collaboration to predict the future trajectories of workers on construction sites, while ensuring data privacy and reducing computational burden. The edge-end acquires multi-view images about the physical scene and extracts multi-scale features with a deep learning-based backbone. In the cloud-end, where the digital world is hosted, a Transformer-based trajectory tracking model is developed to construct a behavioral digital replica comprising of multiple workers’ historical trajectories from the bird’s-eye view perspective. Subsequently, a LSTM-based model, combined with the social pooling mechanism, is deployed to obtain spatiotemporal interactive features from the historical trajectories and predict workers’ future motions. Experiments are conducted on a dataset (WHUT-MF) collected from real-world constructions sites. Our framework achieves 0.528 m in ADE and 0.84 m in FDE on entire WHUT-MF, which demonstrate that the proposed digital twin-based motion forecasting model accurately predicts the future trajectories of workers in various scenarios with potential risks.

FederatedTrust: A solution for trustworthy federated learning

The rapid expansion of the Internet of Things (IoT) and Edge Computing has presented challenges for centralized Machine and Deep Learning (ML/DL) methods due to the presence of distributed data silos that hold sensitive information. To address concerns regarding data privacy, collaborative and privacy-preserving ML/DL techniques like Federated Learning (FL) have emerged. FL ensures data privacy by design, as the local data of participants remains undisclosed during the creation of a global and collaborative model. However, data privacy and performance are insufficient since a growing need demands trust in model predictions. Existing literature has proposed various approaches dealing with trustworthy ML/DL (excluding data privacy), identifying robustness, fairness, explainability, and accountability as important pillars. Nevertheless, further research is required to identify trustworthiness pillars and evaluation metrics specifically relevant to FL models, as well as to develop solutions that can compute the trustworthiness level of FL models. This work examines the existing requirements for evaluating trustworthiness in FL and introduces a comprehensive taxonomy consisting of six pillars (privacy, robustness, fairness, explainability, accountability, and federation), along with over 30 metrics for computing the trustworthiness of FL models. Subsequently, an algorithm named FederatedTrust is designed based on the pillars and metrics identified in the taxonomy to compute the trustworthiness score of FL models. A prototype of FederatedTrust is implemented and integrated into the learning process of FederatedScope, a well-established FL framework. Finally, five experiments are conducted using different configurations of FederatedScope (with different participants, selection rates, training rounds, and differential privacy) to demonstrate the utility of FederatedTrust in computing the trustworthiness of FL models. Three experiments employ the FEMNIST dataset, and two utilize the N-BaIoT dataset, considering a real-world IoT security use case.

Revolutionizing Healthcare: How Machine Learning is Transforming Patient Diagnoses - a Comprehensive Review of AI's Impact on Medical Diagnosis

The integration of machine learning into healthcare heralds a new era where the convergence of technology and human compassion reshapes the very essence of healing. This monumental shift transcends mere technological advancement; it represents a profound evolution in patient care. By unraveling intricate patterns within medical data, machine learning empowers healthcare professionals with early disease detection and precise risk assessment, augmenting human intuition rather than replacing it. This synergy between AI-driven insights and human expertise has led to remarkable achievements, from redefining radiological interpretations to foreseeing infectious disease outbreaks, painting a future where healthcare is not only precise but profoundly patient-centered. Yet, amidst these groundbreaking advancements, ethical considerations stand as pillars guiding responsible innovation. Upholding patient autonomy, ensuring data privacy, and addressing algorithmic bias are essential to maintain trust and integrity. As we navigate this transformative path, the promise of a healthcare landscape where healing becomes a symphony of technology and tradition becomes evident. It is a future where the well-being and hopes of millions are at the core, promising a brighter, more compassionate tomorrow for healthcare, where every diagnosis, treatment, and act of care resonates with the harmony of human expertise and technological marvels.

Optimal and secure peer-to-peer carbon emission trading: A game theory informed framework on blockchain

We address two key challenges towards an effective and accountable emission trading system (ETS). The first is to determine the individual policies while ensuring a fair allocation of costs between the stakeholders to meet an overall environmental target for an industrial ecosystem. The second is to ensure privacy and traceability of shared data when participating in an ETS. Specifically, we propose a mixed-integer nonlinear program (MINLP) for peer-to-peer carbon trading in ETS under fixed carbon tax or cap-and-trade systems. To ensure data privacy and traceability, the MINLP model is integrated with smart contracts on the Ethereum blockchain. The model determines how much the participants buy/sell emission allocations, how much they invest in carbon capture, which capture technologies they select, and how they respond to changes in carbon prices. The planning requires simultaneous decision-making for all participants, which can be obtained as a Generalized Nash Equilibrium (GNE).

Efficient and anonymous password-hardened encryption services

Password-based authentication and encryption schemes are commonly employed to ensure data privacy. Nevertheless, these schemes are vulnerable to brute-force attacks, as user passwords have low-entropy. Password-hardened encryption (PHE) was proposed to combat brute-force attacks by introducing an external crypto service to enforce rate limiting for user requests. However, existing PHE schemes fail to provide user anonymity and need to rely on computationally expensive cryptographic primitives (e.g. zero-knowledge proofs and exponentiations). In this paper, we introduce cross-epoch anonymity in PHE to trade off rate limiting and per-user anonymity. The user requests within the same epoch can be linked by the external crypto service to enforce rate limiting and defend against brute-force attacks, while the requests from different epochs cannot be linked to specific users, ensuring per-user anonymity. Subsequently, we propose an anonymous PHE (APHE) scheme that leverages the trusted execution environment provided by Intel SGX to achieve cross-epoch anonymity. Our scheme achieves both soundness and strong soundness without using zero-knowledge proofs and exponentiations. Sensitive operations are executed within the trusted execution environment, leading to significant performance improvements. The evaluation results demonstrate that our scheme outperforms the state-of-the-art PHE scheme with more than 12/9 times lower latencies for encryption/decryption.

FedChain-Hunter: A reliable and privacy-preserving aggregation for federated threat hunting framework in SDN-based IIoT

In the development of the Industrial Internet of Things (IIoT), cyber threats and attacks have become major issues and concerns in Industry 4.0 due to the negative impacts on the infrastructures and services across organizations. Nevertheless, due to the issues in preserving privacy and transparency, there is a lack of threat intelligence sharing among parties, leading to the low performance in uncovering malicious actors. In fact, the method of gathering and exploiting such data has been getting more crucial in a trend of machine learning (ML) adoption in cybersecurity. In this scenario, Federated Learning (FL) can assume a significant role in constructing an ML-based threat hunting solution for IIoT networks. This can be achieved by harnessing data resources from diverse parties, utilizing a local training strategy that eliminates the need for centralized data collection. Hence, this paper proposes FedChain-Hunter, a blockchain and FL-based threat-hunting framework to mutually seek cyber threats while ensuring data privacy and the transparency in the contribution of data owners. Specifically, Software Defined Networking (SDN) with programmable and flexible security orchestration is used to easily monitor and gather appropriate security events in the IIoT network. In addition, the Fully Homomorphic Encryption (HE) and Differential Privacy (DP) are integrated into the FL scheme to provide strong security and privacy-preserving aggregation for each ML model update. Also, the blockchain adoption offers the transparency, auditability for collaboration and contribution management through a decentralized platform. The experimental results on 5 datasets indicate that FedChain-Hunter can achieve high performance for cyber threat detection with security, reliability, and privacy guarantee.

Harnessing the power of federated learning to advance technology

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, advocating for decentralized, privacy-preserving model training. This study provides a comprehensive evaluation of contemporary FL frameworks TensorFlow Federated (TFF), PySyft, and FedJAX across three diverse datasets: CIFAR-10, IMDb reviews, and the UCI Heart Disease dataset. Our results demonstrate TFF's superior performance on image classification tasks, while PySyft excels in both efficiency and privacy for textual data. The study underscores the potential of FL in ensuring data privacy and model performance, yet emphasizes areas warranting improvement. As the volume of edge devices escalates and the need for data privacy intensifies, refining and expanding FL frameworks become essential for future machine learning deployments.

Exploring the Regulatory Demands and Evolution of Payment Security Regulations for Digital Payment Platforms in Sweden

This article discusses the compliance challenges faced by digital payment platforms in Sweden, including navigating a complex regulatory landscape, meeting stringent security standards, and ensuring data privacy. It examines the impact of technological innovations on payment security, such as biometric authentication and tokenization. The regulatory responses to emerging threats and technologies are explored, including updates to existing regulations and collaboration with industry stakeholders. The article also highlights future trends and challenges in payment security, such as continued technological advancements and the need for user education.

Multiparticipant Federated Feature Selection Algorithm With Particle Swarm Optimization for Imbalanced Data Under Privacy Protection

In real world, data describing the same learning task may be distributed in different institutions (called participants), and these participants cannot share their own data due to the need of privacy protection. How to select an optimal feature subset on the basis of ensuring the data privacy of each participant is an important and challenging topic. At the same time, data on part participants show imbalanced or even miss some classes, further increasing the difficulty of solving this kind of problem. In view of this, by introducing a trusted third party to process and integrate optimal information from participants, this paper proposes a multi-participant federated evolutionary feature selection algorithm for imbalanced data under privacy protection. Firstly, a multi-level joint sample filling strategy with multiple participants (called sampling-rough selection-fine tuning strategy) is proposed to fill imbalanced or empty classes on each participant while ensuring data privacy. Then, a federated evolutionary feature selection method based on particle swarm optimization (PSO) is proposed by periodically sharing the optimal feature subsets obtained by PSOs on participants. Finally, the proposed algorithm is applied to 15 test datasets, and compared with several typical imbalanced feature selection algorithms and two kinds of ensemble feature selection algorithms. The experimental results show that the proposed algorithm can significantly promote the ability of each participant on processing imbalanced datasets, and improve the classification accuracy of obtained feature subsets while protecting the participants' data privacy.

Optimal CBDC design for Ukraine through the lens of privacy and security

The growing popularity of cryptocurrencies has put on the agenda the need to develop an alternative and more regulated digital currency design, including a central bank digital currency (CBDC). The objective of the study is to formulate proposals for the development of the optimal design of the CBDC of Ukraine. The study is based on a review of the literature on digital currencies, cryptocurrencies and legislation on personal data protection, payment security and financial supervision. The implementation of the CBDC in Ukraine is associated with numerous technical and legal risks, including: privacy and data security risks; complications of financial monitoring; contradictions with national and international legislation; banks disintermediation risks. To prevent these risks, a CBDC design is proposed that is compatible with national and international legislation, ensures data privacy and security, facilitates financial tracking, and reduces the risks of disintermediation. The development of the CBDC in Ukraine could have a significant impact on the country's financial system. However, it is essential that the design of the CBDC is carefully considered to mitigate potential risks.

Federated Transfer Learning for Rice-Leaf Disease Classification across Multiclient Cross-Silo Datasets

Paddy leaf diseases encompass a range of ailments affecting rice plants’ leaves, arising from factors like bacteria, fungi, viruses, and environmental stress. Precision agriculture leverages technologies for enhanced crop production, with disease detection being a vital element. Prompt identification of diseases in paddy leaves is critical for curtailing their propagation and reducing crop damage. However, manually diagnosing paddy diseases in regions with vast agricultural areas and limited experts proves immensely difficult. The utilization of machine learning (ML) and deep learning (DL) for diagnosing diseases in agricultural crops appears to be effective and well-suited for widespread application. These ML/DL methods cannot ensure data privacy, as they involve sharing training data with a central server, overlooking competitive and regulatory considerations. As a solution, federated learning (FL) aims to facilitate decentralized training to tackle the identified limitations of centralized training. This paper utilizes the FL approach for the classification of rice-leaf diseases. The manuscript presents an effective approach for rice-leaf disease classification with a federated architecture, ensuring data privacy. We have compiled an unbalanced dataset of rice-leaf disease images, categorized into four diseases with their respective image counts: bacterial blight (1584), brown spot (1440), blast (1600), and tungro (1308). The proposed method, called federated transfer learning (F-TL), maintains privacy for all connected devices using a decentralized client-server setup. Both IID (independent and identically distributed) and non-IID datasets were utilized for testing the F-TL framework after preprocessing. Initially, we conducted an effectiveness analysis of CNN and eight transfer learning models for rice-leaf disease classification. Among them, MobileNetV2 and EfficientNetB3 outperformed the other transfer-learned models. Subsequently, we trained these models using both IID and non-IID datasets in a federated learning environment. The framework’s performance was assessed through diverse scenarios, comparing it with traditional and federated learning models. The evaluation considered metrics like validation accuracy, loss as well as resource utilization such as CPU and RAM. EfficientNetB3 excelled in training, achieving 99% accuracy with 0.1 loss for both IID and non-IID datasets. MobilenetV2 showed slightly lower training accuracy at 98% (IID) and 90% (non-IID) with losses of 0.4 and 0.6, respectively. In evaluation, EfficientNetB3 maintained 99% accuracy with 0.1 loss for both datasets, while MobilenetV2 achieved 90% (IID) and 97% (non-IID) accuracy with losses of 0.6 and 0.2, respectively. Results indicated the F-TL framework’s superiority over traditional distributed deep-learning classifiers, demonstrating its effectiveness in both single and multiclient instances. Notably, the framework’s strengths lie in its cost-effectiveness and data-privacy assurance for resource-constrained edge devices, positioning it as a valuable alternative for rice-leaf disease classification compared to existing tools.

Ensemble Federated Learning Approach for Diagnostics of Multi-Order Lung Cancer.

The early detection and classification of lung cancer is crucial for improving a patient's outcome. However, the traditional classification methods are based on single machine learning models. Hence, this is limited by the availability and quality of data at the centralized computing server. In this paper, we propose an ensemble Federated Learning-based approach for multi-order lung cancer classification. This approach combines multiple machine learning models trained on different datasets allowing for improvising accuracy and generalization. Moreover, the Federated Learning approach enables the use of distributed data while ensuring data privacy and security. We evaluate the approach on a Kaggle cancer dataset and compare the results with traditional machine learning models. The results demonstrate an accuracy of 89.63% with lung cancer classification.

Distributed autoencoder classifier network for small‐scale and scattered COVID‐19 dataset classification

AbstractIn healthcare, small‐scare data are stored with individual entities, such as hospitals, and they are not shared. However, data with one entity are not sufficient for training a machine learning model and therefore cannot be fully utilized. Given that a large amount of small‐scale data is widely distributed between hospitals/individuals, it is necessary to deploy an easy, scalable, and secure distributed computational framework. We aim to aggregate these scattered and small‐scale data to train neural networks and achieve classification and detection on coronavirus disease 2019 (COVID‐19) datasets. We propose a distributed autoencoder (AE) classifier network for this purpose. It contains a central classifier and multiple distributed AEs. The AEs are used as generators. A local generator uses an actual COVID‐19 computed tomography image as the input and outputs a synthetic image. The well‐trained generator provides an image to train the central classifier model. The central classifier network model learns information from all the generated COVID‐19 data using the distributed AE. Experiments are performed using some COVID‐19 datasets. The distributed AE classifier network outperforms all the models that use a single subset, and its performance is similar to that of a regular classifier. The proposed network solves the problem of using small‐scale and scattered COVID‐19 data to train neural networks while ensuring data privacy. The accuracy of the network is the same as that achieved using the entire data.

Selective dissemination of information (SDI) in the age of artificial intelligence (AI)

Purpose In this study, the authors seek to introduce ways that show that in the age of artificial intelligence (AI), selective dissemination of information (SDI) performance can be greatly enhanced by leveraging AI technologies and algorithms. Design/methodology/approach AI holds significant potential for the SDI. In the age of AI, SDI can be greatly enhanced by leveraging AI technologies and algorithms. The authors discuss SDI technique used to filter and distribute relevant information to stakeholders based on the pertinent modern literature. Findings The following conceptual indicators of AI can be utilized for obtaining a better performance measure of SDI: intelligent recommendation systems, natural language processing, automated content classification, contextual understanding, intelligent alert systems, real-time information updates, intelligent alert systems, real-time information updates, adaptive learning, content summarization and synthesis. Originality/value The authors propose the general framework in which AI can greatly enhance the performance of SDI but also emphasize that there are challenges to consider. These include ensuring data privacy, avoiding algorithmic biases, ensuring transparency and accountability of AI systems and addressing concerns related to information overload.

Weighted aggregation through probability based ranking: An optimized federated learning architecture to classify respiratory diseases

Background and ObjectiveRespiratory Diseases are one of the leading chronic illnesses in the world according to the reports by World Health Organization. Diagnosing these respiratory diseases is done through auscultation where a medical professional listens to sounds of air in the lungs for anomalies through a stethoscope. This method necessitates extensive experience and can also be misinterpreted by the medical professional. To address this issue, we introduce an AI-based solution that listens to the lung sounds and classifies the respiratory disease detected. Since the research work deals with medical data that is tightly under wraps due to privacy concerns in the medical field, we introduce a Deep learning solution to classify the diseases and a custom Federated learning (FL) approach to further improve the accuracy of the deep learning model and simultaneously maintain data privacy. Federated Learning architecture maintains data privacy and facilitates a distributed learning system for medical infrastructures.MethodsThe approach utilizes Generative Adversarial Networks (GAN) based Federated learning approach to ensure data privacy. Generative Adversarial Networks generate new data by synthesizing new lung sounds. This new synthesized data is then converted to spectrograms and trained on a neural network to classify four lung diseases, Heart Attack and Normal breathing patterns. Furthermore, to address performance loss during FL, we also propose a new “Weighted Aggregation through Probability-based Ranking (FedWAPR)” algorithm for optimizing the FL aggregation process. The FedWAPR aggregation takes inspiration from exponential distribution function and ranks better performing clients according to it.Results and ConclusionA test accuracy of about 92% was achieved by the trained model while classifying various respiratory diseases and heart failure. Additionally, we developed a novel FedWAPR approach that significantly outperformed the FedAVG approach for the FL aggregate function. A patient can be checked for respiratory diseases using this improved learning approach without the need for extensive sensitive data recording or for making sure the data sample obtained is secure. In a decentralized training runtime, the trained model successfully classifies various respiratory diseases and heart failure using lung sounds with a test accuracy on par with a centralized model.

FL-IIDS: A novel federated learning-based incremental intrusion detection system

With the advantage of analyzing data of multiple work sites comprehensively while ensuring data privacy, federated learning-based intrusion detection systems (IDS) are emerging as a distributed intrusion detection paradigm. Most of these IDS are assumed to work on static data. However, in the actual network environment, the practice of setting data as static will lead to the phenomenon known as catastrophic forgetting, where old classes that have already appeared would be forgotten. In this paper, we propose a novel IDS framework called FL-IIDS to effectively address the catastrophic forgetting problem. Firstly, a new loss function is synthetically designed for local model training. With the new function, the class gradient balance loss function assigns different learning weights to data of the new and old classes so that the learning rate of the new classes would decrease and the memory of the overall old classes would be deepened. Moreover, the sample label smoothing loss function leverages the knowledge distillation method to enhance the local model memory for every specific class of old classes. Secondly, the relay client fusing sample reconstruction is employed to mitigate the spread of catastrophic forgetting globally without compromising data privacy. Extensive experimental results on the UNSW-NB15 dataset and the CICIDS2018 dataset show that our proposed framework improves the memory capability for old classes substantially without affecting the detection effectiveness of the IDS for new classes.

A Comprehensive Analysis of Anonymization Techniques in Ensuring Data Privacy

A Comprehensive Analysis of Anonymization Techniques in Ensuring Data Privacy

Exploration of remote management and an intelligent platform for in-hospital respiratory therapy

The construction of an intelligent remote management platform for respiratory therapy, utilizing artificial intelligence (AI) and the electronic medical record system (EMR), has significant potential to improve the management of respiratory therapy in critically ill patients. This platform includes the development of a dedicated respiratory therapy EMR, the integration of data from multiple mechanical ventilators from different vendors and models, and the utilization of AI-assisted analysis to understand the pathophysiology of respiratory diseases and the complex physiological factors that influence specific interventions, thereby supporting diagnosis, treatment guidance, and prognosis prediction. In addtion, a network will be established to provide seamless connectivity between hospitals and wards. The resulting platform enables the collection of medical device data from multiple points within the hospital, real-time data analysis, and timely alarms, thereby facilitating remote data access, centralization of information, and standardization of data. As a result, the platform enables efficient intra-hospital and inter-hospital doctor-patient management. Despite the benefits offered by this platform, certain challenges need to be addressed, including ensuring data privacy and security, as well as managing the financial and human resources required for its implementation and maintenance. Furthermore, continuous optimization of the platform is crucial, and the clinical use of the platform requires appropriate professional training.