Efficient secure federated learning aggregation framework based on homomorphic encryption by Shengxing YU, Zhong CHEN

“…In order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved urgently.However, the computational cost and communication overhead caused by the encryption scheme would affect the training efficiency.Firstly, in the case of protecting data security and ensuring training efficiency, the Top-K gradient selection method was used to screen model gradients, reducing the number of gradients that need to be uploaded.A candidate quantization protocol suitable for multi-edge terminals and a secure candidate index merging algorithm were proposed to further reduce communication overhead and accelerate homomorphic encryption calculations.Secondly, since model parameters of each layer of neural networks had characteristics of the Gaussian distribution, the selected model gradients were clipped and quantized, and the gradient unsigned quantization protocol was adopted to speed up the homomorphic encryption calculation.Finally, the experimental results show that in the federated learning scenario, the proposed framework can protect data privacy, and has high accuracy and efficient performance.…”
Get full text

Optimizing Industrial IoT Data Security Through Blockchain-Enabled Incentive-Driven Game Theoretic Approach for Data Sharing by Muhammad Noman Sohail, Adeel Anjum, Iftikhar Ahmed Saeed, Madiha Haider Syed, Axel Jantsch, Semeen Rehman

“…To mitigate these challenges, we have proposed a secure and incentive-based data-sharing framework for IIoT systems using blockchain technology. …”
Get full text

Decades in the Making: The Evolution of Digital Health Research Infrastructure Through Synthetic Data, Common Data Models, and Federated Learning by Jodie A Austin, Elton H Lobo, Mahnaz Samadbeik, Teyl Engstrom, Reji Philip, Jason D Pole, Clair M Sullivan

“…The same way that drug trials require infrastructure to support their conduct, digital health also necessitates new and disruptive research data infrastructure. Novel methods such as common data models, federated learning, and synthetic data generation are emerging to enhance the utility of research using RWD, which are often siloed across health systems. …”
Get full text

KAB: A new k-anonymity approach based on black hole algorithm by Lynda Kacha, Abdelhafid Zitouni, Mahieddine Djoudi

“…K-anonymity is the most widely used approach to privacy preserving microdata which is mainly based on generalization. …”
Get full text

Using Federated Learning for Collaborative Intrusion Detection Systems by Matteo Rizzato, Youssef Laarouchi, Christophe Geissler

“…Traditional implementations provide fast and accurate predictions, but require centralised storage of labelled historical data for training. This solution is not always suitable for real-world applications, where regulatory constraints and privacy concerns hamper the collection of sensitive data into a single server. …”
Get full text

Normative framework for the protection against genetic discrimination in Serbia by Petrušić Nevena

“…The analysis has shown that the rules on protection of the genetic data and the use of genetic samples, which are crucially important for prevention of genetic discrimination, have not been harmonized with contemporary ethical and legal standards. …”
Get full text

Edge Computing Oriented Certificateless Sorting Ciphertext Retrieval Scheme by DUAN Jie, GU Wei, ZHANG Shujuan, GONG Xin

“…[Purposes] In order to ensure the privacy and retrievability of cloud data, ciphertext retrieval technology has emerged. …”
Get full text

Characterizing user mobility using mobile sensing systems by Sébastien Faye, Walter Bronzi, Ibrahim Tahirou, Thomas Engel

“…Furthermore, we detail the need to use methods that respect the privacy of users and investigate the possibilities offered by network traces, including Wi-Fi and Bluetooth communication technologies. …”
Get full text

Ethical Considerations for Using Artificial Intelligence in Digital Technologies by William Jorgensen, Matt Bjornsen, Rikke Carlsen

Get full text

Covert surveillance of communications: Compliance with the practice of the European court of human rights by Kovačević Milica

Get full text

THE POSSIBILITY OF USING ELECTRONIC MEDICAL RECORDS FOR CLINICAL OBSERVATION by R. D. Kurbanov, R. Kh. Trigulova

“…It is always necessary to remember that when using EMC for clinical trials, it is first necessary to integrate various types of information, in accordance with the criteria for acceptability of the protocol, elements of clinical trial data, EMC data for only one purpose – to enable cohort identification. …”
Get full text

A secure and efficient user selection scheme in vehicular crowdsensing by Min Zhang, Qing Ye, Zhimin Yuan, Kaihuan Deng

“…In addition, a prediction model based on principal component analysis-enhanced long short-term memory (PCA-Enhanced LSTM) model is constructed by combining the advantages of principal component analysis (PCA) and long short-term memory (LSTM) network. The model uses PCA for data dimensionality reduction to eliminate redundant information and then employs LSTM to process time series data, capture long-term dependencies for more accurate user credit prediction, screen high-quality users, and improve perceived data quality. …”
Get full text

Ethical Challenges in Blood Donation from Viewpoint of Blood Transfusion Policymakers, Experts and Stakeholders: A Qualitative Study by forouzan akrami, Abolfazl Asghari, tooran mohammadi, abbas sedaghat

“…Purposeful sampling and focus group discussion were used to collect data. Data analysis was performed by Graneheim and Lundman inductive content analysis. …”
Get full text

BANK INDONESIA’S ROLE IN MITIGATING ISSUES OF MONETARY ECONOMIC SOVEREIGNTY AND HUMAN RIGHTS by Dara Salsabila

Get full text

New cross-layer reputation mechanism for mobile cloud computing by Mengyang YU, Hui LIN, Youliang TIAN

“…Users are facing increasingly serious security threats such as data leakage and privacy exposure while using various mobile cloud services.Based on the data security and privacy protection for mobile cloud computing research background,combining the cross-layer design and credit mechanism,in the node between the introduction of the MAC layer and network layer in the process of credit evaluation of factors affecting user reputation,to identify and manage internal malicious nodes.The credibility of the simulation results show that the proposed mechanism can effectively resist the internal defamation and multilayer attack,enhance the credibility of mobile terminals,thus improve the mobile cloud service data security and privacy protection.…”
Get full text

WiFi-Based Location Tracking: A Still Open Door on Laptops by Mariana Cunha, Ricardo Mendes, Yves-Alexandre de Montjoye, Joao P. Vilela

“…Location privacy is a major concern in the current digital society, due to the sensitive information that can be inferred from location data. …”
Get full text

Analyzing the concept of solitude with the spatial syntax technique in the spatial organization of rural homes; case Study: Bushehr province by Farshid Mesbah, Behzad Vasigh, Mostafa Masoudinezhad

“…In the next stage, graph analysis technique was used to extract data from the drawn maps using tools such as connectivity, relationship, step depth, metric depth, and angle of view with the help of Depth Map software for sample analysis. …”
Get full text

FFM: Flood Forecasting Model Using Federated Learning by Muhammad Shoaib Farooq, Rabia Tehseen, Junaid Nasir Qureshi, Uzma Omer, Rimsha Yaqoob, Hafiz Abdullah Tanweer, Zabihullah Atal

“…Federated Learning is the most advanced technique of machine learning (ML) that guarantees data privacy, ensures data availability, promises data security, and handles network latency trials inherent in prediction of floods by prohibiting data to be transferred over the network for model training. …”
Get full text

Factors influencing the perceived usability of line pay: An extended technology acceptance model approach by Yogi Tri Prasetyo, Krisna Chandra Susanto, Ko-Hui Chuang, Ruo-Ting Yin, Jia-Wei Chen, Yu-Xuan Zhang, Omar Paolo Benito, Zachariah John A. Belmonte, Maela Madel L. Cahigas, Reny Nadlifatin, Ma. Janice J. Gumasing

“…Utilizing an extended Technology Acceptance Model (TAM), the research integrated additional variables such as social influence, trust, security, and environmental concerns, offering a comprehensive framework to understand user adoption dynamics. 120 Taiwanese participants were surveyed by employing the Purposive Sampling Method and data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). …”
Get full text

Based on model randomization and adaptive defense for federated learning schemes by Gaofeng Yue, Xiaowei Han

“…Abstract Federated Learning (FL) is a privacy-enhancing technique that enables multiple participants to collaboratively train machine learning models without sharing their local data. …”
Get full text