Membership inference attack and defense method in federated learning based on GAN by Jiale ZHANG, Chengcheng ZHU, Xiaobing SUN, Bing CHEN

“…Aiming at the problem that the federated learning system was extremely vulnerable to membership inference attacks initiated by malicious parties in the prediction stage, and the existing defense methods were difficult to achieve a balance between privacy protection and model loss.Membership inference attacks and their defense methods were explored in the context of federated learning.Firstly, two membership inference attack methods called class-level attack and user-level attack based on generative adversarial network (GAN) were proposed, where the former was aimed at leaking the training data privacy of all participants, while the latter could specify a specific participant.In addition, a membership inference defense method in federated learning based on adversarial sample (DefMIA) was further proposed, which could effectively defend against membership inference attacks by designing adversarial sample noise addition methods for global model parameters while ensuring the accuracy of federated learning.The experimental results show that class-level and user-level membership inference attack can achieve over 90% attack accuracy in federated learning, while after using the DefMIA method, their attack accuracy is significantly reduced, approaching random guessing (50%).…”
Get full text

PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks by Walid Remmas, Martin Lints, Jaak Joonas Uudmae

“…Object detection models rely on large-scale, high-quality annotated datasets, which are often expensive, scarce, or restricted due to privacy concerns. Synthetic data generation has emerged as an alternative, yet existing approaches have limitations: generative models lack structured annotations and precise spatial control, while game-engine-based datasets suffer from inaccuracies due to 3D bounding box projections, limited scene diversity, and poor handling of articulated objects. …”
Get full text

Examining the impact of environmental product innovation on perceived brand value considering the mediating role of ethical- aspects in the home appliance industry by Hamidreza Talaie

“…In this study, a convenience sampling method was used. To collect data, a standardized questionnaire was used, whose validity was confirmed by calculating content, convergent, and divergent validity, and its reliability was confirmed through the Cronbach's alpha index. …”
Get full text

Cybersecurity in Smart Railways: Exploring risks, vulnerabilities and mitigation in the data communication services by Tiago Fernandes, João Paulo Magalhães, Wellington Alves

Get full text

SGAK: A Robust ECC-Based Authenticated Key Exchange Protocol for Smart Grid Networks by Akber Ali Khan, Vinod Kumar, Ramakant Prasad, M. Javed Idrisi

Get full text

Sharing traumatic stress research data: assessing and reducing the risk of re-identification by Nancy Kassam-Adams, Kristi Thompson, Marit Sijbrandij, Grete Dyb

“…Background: FAIR Data practices support data sharing and re-use and are essential for advancing science and practice to benefit individuals, families, and communities affected by trauma. …”
Get full text

Integration of data science with the intelligent IoT (IIoT): Current challenges and future perspectives by Inam Ullah, Deepak Adhikari, Xin Su, Francesco Palmieri, Celimuge Wu, Chang Choi

“…Extensive insights into IoT data security, privacy, and challenges are visualized in the context of data science for IoT. …”
Get full text

Global trends of big data analytics in health research: a bibliometric study by Li Yao, Li Yao, Yan Liu, Tingrui Wang, Chunyan Han, Qiaoxing Li, Qinqin Li, Xiaoli You, Tingting Ren, Yinhua Wang

“…Co-occurrence word analysis identified six key research areas: (1) the application of big data analytics in health decision-making; (2) challenges in the technological management of health and medical big data; (3) integration of machine learning with health monitoring; (4) privacy and ethical issues in health and medical big data; (5) data integration in precision medicine; and (6) the use of big data in disease management and risk assessment. …”
Get full text

Islam, Big Data, and Digital Ethics: Challenges in Religious Life in the Digital Age by Agung Saputra, Erni Asneli Asbi

“…These technologies offer opportunities to enhance the efficiency of religious practices, such as prayer reminders, Quran recitation, and zakat distribution, but they also present ethical challenges related to privacy, data misuse, and the erosion of deep spiritual experiences. …”
Get full text

Machine Learning and Data Science in Social Sciences: Methods, Applications, and Future Directions by Elias Dritsas, Maria Trigka

“…We review current strategies for responsible AI deployment, including regulatory frameworks, human-centered design principles, and privacy-preserving methods. By synthesizing methodological advances and cross-cutting challenges, this study provides a focused and interdisciplinary roadmap for the rigorous and equitable use of AI in social science research.…”
Get full text

The application of distributed autonomous organization governance mechanisms to civic medical data management by James Cunningham, Nigel Davies, Sarah Devaney, Søren Holm, Mike Harding, Victoria Neumann, John Ainsworth

“…The mechanisms employed by DAOs has the potential to be generalized beyond their core financial domain to a wide range of use cases. In the medical field the use of blockchain and DAOs can provide secure and transparent access to medical data, while ensuring patient privacy. …”
Get full text

Harnessing digital health data for suicide prevention and care: A rapid review by Laura Bennett-Poynter, Sridevi Kundurthi, Reena Besa, Dan W. Joyce, Andrey Kormilitzin, Nelson Shen, James Sunwoo, Patrycja Szkudlarek, Lydia Sequiera, Laura Sikstrom

“…The primary aim of this study is to identify considerations for the collection and use of digital health data for suicide prevention and care. …”
Get full text

Data Mining Techniques for Predictive Maintenance in Manufacturing Industries a Comprehensive Review by Chinthamu Narender, Ashish, P Mathiyalagan, B Devananda Rao, S Kannadhasan, M Suganya

“…Predictive maintenance (PdM) is one of the major methods used in modern manufacturing to realize downtime minimization, lower the cost of maintenance and maximize machine service life by analyzing the collected data using data mining methodologies. …”
Get full text

CHALLENGES AND OPPORTUNITIES IN THE IMPLEMENTATION OF BIG DATA ANALYTICS IN MANAGEMENT INFORMATION SYSTEMS IN BANGLADESH by Golam Mustafa, MD. Nurullah Rabbani, Avishek Nath, Md Mehedi Hasan Emon

“…The findings reveal that organizations in Bangladesh encounter challenges related to limited technological infrastructure, data security and privacy concerns, skill shortages, and regulatory complexities. …”
Get full text

Big data applications in intelligent transport systems: a bibliometric analysis and review by Mahbub Hassan, Hridoy Deb Mahin, Abdullah Al Nafees, Arpita Paul, Saikat Sarkar Shraban

“…We found that ethical, privacy, and security concerns related to the use of Big Data in ITS have received limited attention. …”
Get full text

Blockchain-based and verifiable multidimensional data aggregation and sharing scheme for smart grid by Jianwei CHEN, Shuyu WANG, Meiping ZHANG, Zhenping ZHANG

“…Aiming at the problem that how to support lightweight multi-dimensional data aggregation, achieve double-end integrity verification of multi-dimensional data in the overall process of the system, and deal with the centralization of cloud servers, a blockchain-based and verifiable multidimensional data aggregation and sharing scheme for smart grid was proposed.Firstly, in order to meet the demand for fine-grained analysis of power data in smart grid, privacy-preserving multidimensional data aggregation was achieved by using masked values and Horner’s rule.On this basis, for the data integrity verification problem of the existing data aggregation scheme in the sharing of cloud storage data with the third party, a new signature algorithm was designed by borrowing the RSA-based multiplicative homomorphic commitment scheme and homomorphic hash function homomorphism, which enabled the cloud server to verify the integrity of aggregated data and be used for integrity verification in the data sharing phase, i.e., it achieved double-end verifiability of cloud storage data and was resistant to internal attacks.Meanwhile, an aggregated data sharing architecture based on federated chain multichain was proposed to effectively avoid centralisation problems such as single-machine processing bottleneck and vulnerability to attacks.The theoretical analysis proves the security of the scheme.Performance experiments show that the proposed scheme has lower computation and communication costs compared with existing schemes.…”
Get full text

Blockchain-based and verifiable multidimensional data aggregation and sharing scheme for smart grid by Jianwei CHEN, Shuyu WANG, Meiping ZHANG, Zhenping ZHANG

“…Aiming at the problem that how to support lightweight multi-dimensional data aggregation, achieve double-end integrity verification of multi-dimensional data in the overall process of the system, and deal with the centralization of cloud servers, a blockchain-based and verifiable multidimensional data aggregation and sharing scheme for smart grid was proposed.Firstly, in order to meet the demand for fine-grained analysis of power data in smart grid, privacy-preserving multidimensional data aggregation was achieved by using masked values and Horner’s rule.On this basis, for the data integrity verification problem of the existing data aggregation scheme in the sharing of cloud storage data with the third party, a new signature algorithm was designed by borrowing the RSA-based multiplicative homomorphic commitment scheme and homomorphic hash function homomorphism, which enabled the cloud server to verify the integrity of aggregated data and be used for integrity verification in the data sharing phase, i.e., it achieved double-end verifiability of cloud storage data and was resistant to internal attacks.Meanwhile, an aggregated data sharing architecture based on federated chain multichain was proposed to effectively avoid centralisation problems such as single-machine processing bottleneck and vulnerability to attacks.The theoretical analysis proves the security of the scheme.Performance experiments show that the proposed scheme has lower computation and communication costs compared with existing schemes.…”
Get full text

A collaborative data storage with incentive mechanism for blockchain-based IoV by Quan Shi, Lankai Wang, Chen Chen

“…As the volume of data in the Internet of Vehicles (IoV) continues to grow, challenges such as insufficient storage capacity and potential privacy breaches become more pronounced. …”
Get full text

Highly Secure and Adaptive Multisecret Sharing for Reversible Data Hiding in Encrypted Images by Jiang-Yi Lin, Ching-Chun Chang, Chin-Chen Chang, Chin-Feng Lee

“…Reversible data hiding in encrypted images (RDHEI) is a technique that not only allows the cover images can be fully restored without any loss of information after the embedded data has been extracted but also ensures the confidentiality within the cover images. …”
Get full text

A smart grid data sharing scheme supporting policy update and traceability by Xiaodong Yang, Ke Yao, Songyu Li, Xiaoni Du, Caifen Wang

“…Finally, the analysis results show that this scheme can protect the privacy of smart grid data, verify the integrity of smart grid data, resist collusion attacks and track the identity of malicious users who leak private keys, and its efficiency is better than similar data sharing schemes.…”
Get full text