Privacy-preserving Techniques Research Articles

Distributed Differentially Private Ranking Aggregation

A key step in cooperative decision-making is for all participants to achieve a consensus that avoids individual favoritism. To reach a consensus, a quantitative systematic mechanism is sometimes preferred. An example of such a mechanism is ranking aggregation, where the task is to rank elements in a certain order. While participating in ranking activities, it is also critical under certain circumstances to protect each decision maker’s preference. A promising privacy-preserving technique that is suitable for such a need is differential privacy (DP), which ensures plausible deniability of the protected information with rigorous mathematical guarantee and adjustable privacy level. A concern of the standard DP model is its assumption of letting a curator collect and analyze sensitive information, where in practical situations such a trusted independent curator may not exist. This article proposed a mechanism to solve the above issue using the distributed DP (DDP) framework. The proposed mechanism collects locally differential private rankings from individuals, and then randomly permutes pairwise rankings using a shuffle model to further amplify privacy protection. The final representative is produced by hierarchical rank aggregation (HRA). The mechanism was theoretically analyzed and experimentally compared against the existing methods and demonstrated competitive results in both output accuracy and privacy protection.

Ethical considerations in data science: Balancing privacy and utility

As data science continues to permeate diverse domains, the ethical interplay between privacy and utility has emerged as a critical concern. This study meticulously investigates this intricate balance by examining established ethical frameworks, scrutinising the ethical implications of federated learning, and proposing a user-centric approach to obtaining informed consent. A total of 243 participants contributed to the study, providing insights from various demographic backgrounds. The investigation into ethical framework adaptation revealed a nuanced landscape of perspectives. While a significant proportion acknowledged the potential of ethical frameworks to address privacy-utility complexities, a diversity of viewpoints underscored the ongoing need for their refinement. Examining federated learning's ethical implications exposed heightened concerns about algorithmic biases and transparency challenges, highlighting the urgency of addressing fairness and accountability in privacy-preserving techniques. Synthesising these findings, the study underscores the evolving nature of ethical considerations in data science and the imperative for continual recalibration. The implications extend beyond academia, offering actionable insights for policymakers, industry practitioners, educators, and stakeholders. The study concludes by recognizing its limitations and advocating for further exploration, emphasising the need for collaborative efforts to create an ethical data landscape that safeguards societal values and individual rights.

A Study of Federated Learning with Internet of Things for Data Privacy and Security using Privacy Preserving Techniques

Abstract: Privacy leakage that occurs when many IoT devices are utilized for training centralized models, a new distributed learning framework known as federated learning was created, where devices train models together while keeping their private datasets local. In a federated learning setup, a central aggregator coordinates the efforts of several clients working together to solve machine learning issues. The privacy of each device's data is protected by this setup's decentralized training data. Federated learning reduces traditional centralized machine learning systems' systemic privacy issues and costs by emphasizing local processing and model transfer. Client information is stored locally and cannot be copied or shared. By utilizing a centralized server, federated learning enables each participant's device to collect data locally for training purposes before sending the resulting model to the server for aggregate and subsequent distribution. As a means of providing a comprehensive review and encouraging further research into the topic, we introduce the works of federated learning from five different vantage points: data partitioning, privacy method, machine learning model, communication architecture, and systems heterogeneity. Then, we organize the issues plaguing federated learning today and the potential avenues for a prospective study. Finally, we provide a brief overview of the features of existing federated knowledge and discuss how it is currently being used in the field.

Ensuring data confidentiality and integrity in edge computing environments : A security and privacy perspective

This study examines, from a security and privacy standpoint, the significant obstacles to maintaining data integrity and confidentiality in edge computing contexts. Data security at the edge becomes critical as more and more edge devices proliferate and generate large volumes of sensitive data. The review of the literature looks at edge computing security problems that currently exist and discusses fixes to protect data integrity and confidentiality. The article explores various vulnerabilities, emphasizing the necessity for strong security systems, including data exposure risks and integrity concerns. It examines secure communication protocols, access control methods, and encryption techniques as crucial risk-reduction instruments. Anonymization and differential privacy are two privacy-preserving techniques that are investigated to find a middle ground between user privacy and data value. The article provides real-world insights through case studies and actual implementations, and it lays out metrics and evaluation criteria for determining how successful security measures are. Finally, the report highlights the need of addressing data security in changing edge computing settings and offers future directions and research difficulties.

PRIVACY-AWARE MALARIA DETECTION: U-NET MODEL WITH K-ANONYMITY FOR CONFIDENTIAL IMAGE ANALYSIS

Malaria detection through cell image analysis is essential for early diagnosis and effective treatment, as timely detection can significantly reduce the risk of severe health complications. However, this process raises substantial privacy concerns due to the sensitivity of medical data. This study presents a U-Net model combined with k-anonymity to enhance data security while maintaining high accuracy. The model features a custom Spatial Attention mechanism for improved segmentation performance and incorporates advanced techniques to focus on critical image features. K-Anonymity adds controlled noise to protect data privacy by obfuscating sensitive information. The model achieved a validation accuracy of 99.60%, a Dice score of 99.61%, precision of 99.42%, recall of 99.96%, and an F1 score of 99.69% on malaria cell images. When applied to the Cactus dataset, a real dataset, in agriculture, it achieved an accuracy of 98.58%, an F1 Score of 98.44%, a Dice Score of 95.08%, a Precision of 98.04%, and a Recall of 98.86%, demonstrating its strong generalization capability. These results highlight the effectiveness of integrating privacy-preserving techniques with advanced neural network architectures, improving both security and performance in diverse image analysis applications.

Navigating Legal and Ethical Boundaries: Safeguarding Personal Health Data in International Research Collaboration

Abstract This study delves into the four characteristics of data accessibility across seven APEC countries, identifying key regulatory disparities in utilizing health-related data for medical research, including the potential reuse of health-related data, inconsistencies in anonymization or de-identification standards, and varied legal protection requirements based on the data’s origin. To foster cross-jurisdictional sharing of personal health data and fortify privacy security in China, this paper proposes the following strategies: implementing specialized legislation concerning health-related data, developing a Chinese version of the De-Identification Decision-Making Framework, leveraging advanced cryptographic privacy-preserving techniques in biomedical research, and employing data transfer and usage agreements.

Balancing innovation and privacy : A machine learning perspective

As digital innovation advances, concerns surrounding privacy escalate. This manuscript explores the intricate relationship between machine learning and privacy preservation. Beginning with a comprehensive literature review, we delve into the current state of privacy in the digital age and examine machine learning’s role in addressing these concerns. The manuscript highlights key privacy-preserving techniques, including homomorphic encryption, differential privacy, and federated learning, providing in-depth insights into their applications and real-world implementations. Anticipating future challenges and trends, we recommend maintaining a delicate equilibrium between innovation and privacy in the dynamic landscape of machine learning.

Exploring Privacy-Preserving Disease Diagnosis: A Comparative Analysis

In the healthcare sector, data is considered as a valuable asset, with enormous amounts generated in the form of patient records and disease-related information. Leveraging machine learning techniques enables the analysis of extensive datasets, unveiling hidden patterns in diseases, facilitating personalized treatments, and forecasting potential health issues. However, the flourish of online diagnosis and prediction still faces some challenges related to information security and privacy as disease diagnosis technologies utilizes a lot of clinical records and sensitive patient data. Hence, it becomes imperative to prioritize the development of innovative methodologies that not only advance the accuracy and efficiency of disease prediction but also ensure the highest standards of privacy protection. This requires collaborative efforts between researchers, healthcare practitioners, and policymakers to establish a comprehensive framework that addresses the evolving landscape of healthcare data while safeguarding individual privacy. Addressing this constraint, numerous researchers integrate privacy preservation measures with disease prediction techniques to develop a system capable of diagnosing diseases without compromising the confidentiality of sensitive information. The survey paper conducts a comparative analysis of privacy-preserving techniques employed in disease diagnosis and prediction. It explores existing methodologies across various domains, assessing their efficacy and trade-offs in maintaining data confidentiality while optimizing diagnostic accuracy. The review highlights the need for robust privacy measures in disease prediction, shortcomings related to existing techniques of privacy preserving disease diagnosis, and provides insights into promising directions for future research in this critical intersection of healthcare and privacy preservation.

Privacy-preserving consensus via edge-based state decomposition

This paper makes further generalisations based on the application of edge-based state decomposition methods on average consensus. The edge-based state decomposition method is a privacy-preserving technique that leverages the number of neighbours to decompose node information, effectively safeguarding the privacy of nodes in average consensus, even in the absence of reliable neighbours. Building upon this method, our research expands its applicability to bipartite consensus and scale consensus. In bipartite consensus, the method can also accurately achieve consensus while guaranteeing privacy. In contrast, scale consensus effectively protects the privacy of the final consistency result. In addition, this paper refines the privacy proofs for different enemies. Finally, the simulation results presented at the end of the paper validate the effectiveness of the proposed approach.

Privacy-First Paradigm for Dynamic Consent Management Systems: Empowering Data Subjects through Decentralized Data Controllers and Privacy-Preserving Techniques

This paper explicitly focuses on utilizing blockchain technology in dynamic consent management systems with privacy considerations. While blockchain offers improved security, the potential impact on entities’ privacy must be considered. Through a critical investigation of available contributions to the present state of the art of blockchain-based dynamic consent management systems, we highlight the limitations of plaintext storage and the processing of subject data/consent on the blockchain, which can compromise privacy. We stress the significance of keeping encrypted subject data/consent on the blockchain and sharing it in encrypted form with data controllers and requesters to guarantee privacy and security. Our proposed model demonstrates the usefulness of privacy-preserving techniques, underscoring the decentralization of the abstract entity data controller to enhance subject data/consent privacy. Additionally, we suggest the integration of privacy-enhancing technologies such as secure multi-party computation, homomorphic encryption, and differential privacy with blockchain to accomplish both security and privacy, aligning with the data sharing practices outlined in the General Data Protection Regulation (GDPR) in Europe.

PLA—A Privacy-Embedded Lightweight and Efficient Automated Breast Cancer Accurate Diagnosis Framework for the Internet of Medical Things

The Internet of Medical Things (IoMT) can automate breast tumor detection and classification with the potential of artificial intelligence. However, the leakage of sensitive data can cause harm to patients. To address this issue, this study proposed an intrauterine breast cancer diagnosis method, namely “Privacy-Embedded Lightweight and Efficient Automated (PLA)”, for IoMT, which represents an approach that combines privacy-preserving techniques, efficiency, and automation to achieve our goals. Firstly, our model is designed to achieve lightweight classification prediction and global information processing of breast cancer by utilizing an advanced IoMT-friendly ViT backbone. Secondly, PLA protects patients’ privacy by federated learning, taking the classification task of breast cancer as the main task and introducing the texture analysis task of breast cancer images as the auxiliary task to train the model. For our PLA framework, the classification accuracy is 0.953, the recall rate is 0.998 for the best, the F1 value is 0.969, the precision value is 0.988, and the classification time is 61.9 ms. The experimental results show that the PLA model performs better than all of the comparison methods in terms of accuracy, with an improvement of more than 0.5%. Furthermore, our proposed model demonstrates significant advantages over the comparison methods regarding time and memory.

Evaluating Cluster-Based Synthetic Data Generation for Blood-Transfusion Analysis

Synthetic data generation is becoming an increasingly popular approach to making privacy-sensitive data available for analysis. Recently, cluster-based synthetic data generation (CBSDG) has been proposed, which uses explainable and tractable techniques for privacy preservation. Although the algorithm demonstrated promising performance on simulated data, CBSDG has not yet been applied to real, personal data. In this work, a published blood-transfusion analysis is replicated with synthetic data to assess whether CBSDG can reproduce more complex and intricate variable relations than previously evaluated. Data from the Dutch national blood bank, consisting of 250,729 donation records, were used to predict donor hemoglobin (Hb) levels by means of support vector machines (SVMs). Precision scores were equal to the original data results for both male (0.997) and female (0.987) donors, recall was 0.007 higher for male and 0.003 lower for female donors (original estimates 0.739 and 0.637, respectively). The impact of the variables on Hb predictions was similar, as quantified and visualized with Shapley additive explanation values. Opportunities for attribute disclosure were decreased for all but two variables; only the binary variables Deferral Status and Sex could still be inferred. Such inference was also possible for donors who were not used as input for the generator and may result from correlations in the data as opposed to overfitting in the synthetic-data-generation process. The high predictive performance obtained with the synthetic data shows potential of CBSDG for practical implementation.

Genomic Data Analysis with Variant of Secure Multi-Party Computation Technique

The increasing availability of genomic data for research purposes necessitates innovative approaches to ensure privacy while facilitating collaborative analysis. This study explores the integration of a variant of Secure Multi-Party Computation (SMPC) techniques into genomic data analysis. The conventional challenges of sharing sensitive genetic information among multiple entities, such as research institutions or healthcare providers, are addressed by leveraging advanced cryptographic protocols. The research focuses on the development and implementation of a secure framework for collaborative genomic data analysis using an adapted SMPC variant. This variant is designed to efficiently handle the complexities of genetic data while ensuring robust privacy preservation. By encrypting individual genomic inputs and enabling computations without revealing the raw data, the proposed SMPC variant facilitates joint analyses, contributing to advancements in personalized medicine, disease research, and genetic epidemiology. The variants of SMPC, namely oblivious transfer protocol, is used, this allows the receiver to obtain one out of several pieces of information forwarded by the sender without revealing which one they obtained. It can be integrated into SMPC protocols for enhancing the privacy with less effort and cost. The proposed mechanism involves the validation of the SMPC variant through simulations using real-world genomic datasets and assessing its performance in terms of computational efficiency and privacy preservation. Results from experiments demonstrate the feasibility and effectiveness of the proposed technique in enabling secure multi-party genomic data analysis. This research contributes to the evolving landscape of privacy-preserving techniques in genomics, offering a promising avenue for collaborative research without compromising the confidentiality of sensitive genetic information.

A privacy-preserving federated learning with a secure collaborative for malware detection models using Internet of Things resources

The rise in malware attacks presents a growing security threat in today’s digital landscape, emphasizing the need for advanced malware detection methodology. While numerous detection systems utilizing methodologies like machine learning (ML) have been developed, they often fail to detect new and unknown malware in real time. This is because their malware datasets are generated with a very limited source and are not dynamic for up-to-date malware. Thus, with of the growth of the Internet of Things, malware have also increasingly grown, which makes current malware detection systems outdated in a short time. Therefore, IoT device resources can be exploited for building malware datasets having various types of malware families. In addition, the approach of collecting data from IoT devices and training them in a centralized cloud (CC) server is no longer acceptable due to this approach incurs significant security and privacy issues. This paper proposes PPFL-SC, an efficient privacy-preserving federated learning with a secure collaborative supporting verification. A group-oblivious signcryption cryptography is designed to be used as a privacy-preserving technique for federated learning. The CC server aggregates data without compromising individual data privacy. Moreover, the Stackelberg incentive model is designed as an incentive mechanism for encouraging IoT devices to collaborate through their heterogeneous dataset in a malware detection model. Thus, the proposed incentive mechanism is capable of increasing the participation of IoT devices and decreasing their dropping out during model updating. A security analysis confirms that PPFL-SC fulfills all security requirements for privacy-preserving federated learning. Real-world dataset experiments validate the efficiency and practicality of the proposed PPFL-SC.

Edge AI and On-Device Machine Learning For Real Time Processing

Edge Artificial Intelligence (Edge AI) and on-device machine learning represent significant advancements in computing paradigms, enabling real-time data processing directly at the edge of the network. This approach minimizes the need for centralized cloud-based processing, thereby reducing latency, enhancing privacy, and improving operational efficiency. This paper provides a comprehensive review of Edge AI and on-device machine learning, focusing on their applications, challenges, and future directions. Key applications include smart home devices, healthcare monitoring, autonomous vehicles, and smart city infrastructure, where local data processing facilitates immediate responses and decision-making. However, deploying AI models on edge devices introduces challenges related to model compression, limited computational resources, and power constraints. Security and privacy concerns also arise, necessitating robust data protection and privacy-preserving techniques. Furthermore, the paper explores emerging technologies such as 5G integration and advances in AI hardware, which are expected to drive future developments in Edge AI. Research directions are highlighted, emphasizing the need for new algorithms tailored to edge environments and enhancements in system robustness and reliability. By addressing these challenges and leveraging emerging technologies, Edge AI is poised to transform a wide range of sectors, offering enhanced real-time processing capabilities and paving the way for innovative applications.

Enabling Real-Time AI at the Edge: Federated Learning Framework with Privacy Preservation

This abstract introduces a federated learning framework designed for edge computing environments, enabling real-time AI applications while safeguarding user privacy. The framework leverages distributed edge devices for collaborative model training without central data aggregation, incorporating privacy-preserving techniques like differential privacy and secure aggregation. Experimental validation demonstrates its effectiveness in maintaining model accuracy and ensuring data confidentiality, supporting its suitability for edge-based AI implementations.

Federated Learning Trade-Offs: A Systematic Review of Privacy Protection and Performance Optimization

Federated Learning (FL) is an innovative approach in Artificial Intelligence (AI) that enhances privacy by avoiding centralized data storage and performing learning directly on users' devices. However, this method introduces new privacy concerns, especially during the training phase and when exchanging parameters between servers and clients. Although various privacy-preserving solutions have been developed to address these issues, integrating these mechanisms can lead to increased communication and computational overheads. This, in turn, may affect data utility and the performance metrics of learning systems. This paper presents a systematic literature review of key methods and metrics that help strike a balance between privacy and other performance aspects in FL applications, such as accuracy, loss, convergence time, utility, and overheads in communication and computation. The review offers a comprehensive overview of recent privacy-preserving techniques in FL across different applications, with a special emphasis on quantitative privacy assessment approaches. It aims to highlight the need for balancing privacy with practical requirements in real-world FL scenarios, while also identifying challenges, unresolved issues, and potential areas for future research.

Federated Learning; Privacy Preserving Machine Learning for Decentralized Data


 
 
 
 Federated learning represents a compelling solution for tackling the privacy challenges inherent in decentralized and distributed environments when it comes to machine learning. This scholarly paper delves deep into the realm of federated learning, encompassing its applications and the latest privacy-preserving techniques used for training machine learning models in a decentralized manner. We explore the reasons behind the adoption of federated learning, highlight its advantages over conventional centralized approaches, and examine the diverse methods employed to safeguard privacy within this framework. Furthermore, we scrutinize the current obstacles, unresolved research queries, and the prospective directions within this rapidly developing field
 
 
 

HealthBlock: A Blockchain-IoT Fusion for Secure Healthcare Data Exchange

Managing healthcare data while ensuring its security and privacy is critical to providing quality care to patients. However, traditional approaches to healthcare data sharing have limitations, including the risk of data breaches and the lack of privacy-preserving mechanisms. This research paper proposes a novel hybrid blockchain-IoT approach for privacy-preserving healthcare data sharing that addresses these challenges. Our system incorporates a private blockchain for protected and tamper-proof data sharing, with privacy-preserving techniques such as differential privacy and homomorphic encryption to protect patient data. IoT devices are utilized to collect and transmit real-time data, equipped with privacy-preserving mechanisms such as data anonymization and secure transmission protocols. Our approach achieved an accuracy rate of 98% for access control and a 99.6% success rate for data privacy protection. Furthermore, our proposed system demonstrated improved data storage and retrieval performance, with a data storage overhead reduction of up to 86% and a data retrieval time reduction of up to 81%. These results indicate the potential of our approach to enhance the security, privacy, and efficiency of healthcare data management, contributing to improved patient care outcomes.

Multi-level personalized k-anonymity privacy-preserving model based on sequential three-way decisions

K-anonymity is a widely used privacy-preserving technique which defends against linking attacks by suppression and generalization. The existing k-anonymity algorithms prevent attackers from illegally obtaining private information by constraining at least k records in an equivalence group. However, this unified anonymity method ignores individual differences and leads to a large amount of information loss. To this end, we introduce sequential three-way decisions into k-anonymity, using a dynamic k-value sequence instead of the fixed k-value to achieve personalized k-anonymity. Specifically, we first construct a hierarchical decision table for k-anonymity by attribute generalization trees and sensitive decision values provided with users. Then, we propose a multi-level personalized k-anonymity privacy-preserving model based on sequential three-way decisions, where we anonymize the partitioning granular data with a dynamic k-value sequence, respectively. Furthermore, we present three practical algorithms to implement the proposed model and discuss the differences between them. Finally, the experimental results demonstrate that the proposed model not only provides a more flexible anonymization method to achieve personalized anonymity, but greatly reduces the information loss. This study provides a complete framework for multi-level privacy protection and enriches the application of sequential three-way decisions.