Data Privacy Protection Research Articles

PTF-FSR: A Parameter Transmission-Free Federated Sequential Recommender System

Sequential recommender systems, as a specialized branch of recommender systems that can capture users’ dynamic preferences for more accurate and timely recommendations, have made significant progress. Recently, due to increasing concerns about user data privacy, some researchers have implemented federated learning for sequential recommendation, a.k.a., Federated Sequential Recommender Systems (FedSeqRecs), in which a public sequential recommender model is shared and frequently transmitted between a central server and clients to achieve collaborative learning. Although these solutions mitigate user privacy to some extent, they present two significant limitations that affect their practical usability: (1) They require a globally shared sequential recommendation model. However, in real-world scenarios, the recommendation model constitutes a critical intellectual property for platform and service providers. Therefore, service providers may be reluctant to disclose their meticulously developed models. (2) The communication costs are high as they correlate with the number of model parameters. This becomes particularly problematic as the current FedSeqRec will be inapplicable when sequential recommendation marches into a large language model era. To overcome the above challenges, this article proposes a parameter transmission-free federated sequential recommendation framework (PTF-FSR), which ensures both model and data privacy protection to meet the privacy needs of service providers and system users alike. Furthermore, since PTF-FSR only transmits prediction results under privacy protection, which are independent of model sizes, this new federated learning architecture can accommodate more complex and larger sequential recommendation models. Extensive experiments conducted on three widely used recommendation datasets, employing various sequential recommendation models from both ID-based and ID-free paradigms, demonstrate the effectiveness and generalization capability of our proposed framework. To facilitate future research in this direction, we release our code at https://github.com/hi-weiyuan/PTF-FSR .

Class-Hidden Client-Side Watermarking in Federated Learning

Federated learning consists of a central aggregator and multiple clients, forming a distributed structure that effectively protects data privacy. However, since all participants can access the global model, the risk of model leakage increases, especially when unreliable participants are involved. To safeguard model copyright while enhancing the robustness and secrecy of the watermark, this paper proposes a client-side watermarking scheme. Specifically, the proposed method introduces an additional watermark class, expanding the output layer of the client model into an N+1-class classifier. The client’s local model is then trained using both the watermark dataset and the local dataset. Notably, before uploading to the server, the parameters of the watermark class are removed from the output layer and stored locally. Additionally, the client uploads amplified parameters to address the potential weakening of the watermark during the aggregation. After aggregation, the global model is distributed to the clients for local training. Through multiple rounds of iteration, the saved watermark parameters are continuously updated until the global model converges. On the MNIST, CIFAR-100, and CIFAR-10 datasets, the watermark detection rates on VGG-16 and ResNet-18 reached 100%. Furthermore, extensive experiments demonstrate that this method has minimal impact on model performance and exhibits strong robustness against pruning and fine-tuning attacks.

Data Security and Privacy Protection in Artificial Intelligence Models: Challenges and Defense Mechanisms

Artificial intelligence (AI) and deep learning algorithms are advancing rapidly, with these emerging technologies being widely applied in areas such as audio-visual recognition and natural language processing. However, in recent years, researchers have identified several security risks in current mainstream AI models, which could hinder the further development of AI technologies. As a result, the issues of data security and privacy protection in AI models have become a focus of research. The data and privacy leakage problems are primarily studied from two perspectives: data leakage based on model outputs and data leakage based on model updates. In the context of model output-based data leakage, the study discusses the principles and research status of model theft attacks, model inversion attacks, and membership inference attacks. In the context of model update-based data leakage, the research focuses on how attackers can steal private data during the distributed training process. Regarding data and privacy protection, three common defense methods are primarily studied: model structure defenses, information obfuscation defenses, and query control defenses. This paper reviews the cutting-edge research achievements in the field of data security and privacy protection in AI deep learning models, focusing on the theoretical foundations, key findings, and related applications of data theft and defense technologies in AI deep learning models. Keywords: Artificial Intelligence, Data Security, Privacy Leakage, Privacy Protection

Physical unclonable in-memory computing for simultaneous protecting private data and deep learning models

Compute-in-memory based on resistive random-access memory has emerged as a promising technology for accelerating neural networks on edge devices. It can reduce frequent data transfers and improve energy efficiency. However, the nonvolatile nature of resistive memory raises concerns that stored weights can be easily extracted during computation. To address this challenge, we propose RePACK, a threefold data protection scheme that safeguards neural network input, weight, and structural information. It utilizes a bipartite-sort coding scheme to store data with a fully on-chip physical unclonable function. Experimental results demonstrate the effectiveness of increasing enumeration complexity to 5.77 × 1075 for a 128-column compute-in-memory core. We further implement and evaluate a RePACK computing system on a 40 nm resistive memory compute-in-memory chip. This work represents a step towards developing safe, robust, and efficient edge neural network accelerators. It potentially serves as the hardware infrastructure for edge devices in federated learning or other systems.

Improving Ethical Leadership in Sustainable Public Health Through Fractal AI

This study explores innovative, ethical leadership approaches using artificial intelligence (AI) and fractal geometry in public health while fostering sustainable business practices within public health systems. The research employs a qualitative methodology based on case studies, secondary data analysis, and fractal-based AI algorithm evaluations. It examines advanced algorithms' technical applications in public health settings, improving data privacy, copyright, and intellectual property protection. The study finds that fractal algorithms offer robust solutions for promoting ethical leadership in AI-driven public health systems. Fractal geometry's complexity and self-similarity improve predictive modeling, resource allocation, and system transparency while ensuring legal and ethical compliance. By applying fractal algorithms, public health organizations can improve privacy protection, intellectual property management, and ethical governance. The study highlights the need for further research on practical applications, optimization of fractal algorithms, and overcoming the computational demands associated with their deployment in public health. Ethical leadership approaches supported by fractal algorithms can drive more equitable and secure public health interventions, enhancing trust in AI-driven solutions and reducing healthcare access and outcomes disparities. This research presents a novel integration of fractal geometry and AI to address critical ethical issues in public health, providing innovative solutions for data privacy, intellectual property protection, and ethical leadership practices.

Advancing Emotion Recognition in Wearable Devices: Core Technologies, Challenges and Practical Solutions

This paper reviews the advancements and challenges in emotion recognition systems, focusing on their applications in wearable devices. It examines core technologiesmultimodal data fusion, deep learning models, and personalized frameworksin addressing critical issues such as data quality, computational efficiency, and privacy protection. By highlighting innovative solutions, including edge computing, lightweight architectures, and advanced privacy-preserving techniques, the paper emphasizes their role in enhancing the robustness, scalability, and security. By integrating real-world applications with state-of-the-art methodologies, this review underscores the transformative potential of wearable emotion recognition technologies for enhancing well-being and daily life. This review also examines current challenges in emotion recognition and provides potential solutions to address these issues

Advancing Genetic Engineering through AI: Sequencing and Editing Innovations

As an important part of modern biotechnology, genetic engineering is widely used in fields such as disease treatment, agricultural improvement, and environmental protection. Gene sequencing technology, especially next-generation sequencing technology, provides a powerful tool for studying biological genetic information. However, with the rapid growth of genomic data, how to efficiently and accurately analyze and apply this huge data has become a major challenge facing genetic engineering. In recent years, artificial intelligence (AI) technology, especially deep learning, has been widely used in the automated processing of large-scale data and has shown great potential in genetic engineering. AI technology not only shows advantages in gene editing optimization, genetic variation detection and genome association analysis, but also significantly improves the efficiency and accuracy of genetic data analysis. Although AI has brought many conveniences in genetic engineering, challenges such as technology transparency, data quality issues, and ethics and privacy protection still need to be solved. This article explores the application of artificial intelligence in genetic engineering sequencing and data analysis, analyzes how AI can improve the efficiency and accuracy of genetic data analysis, and discusses the potential contribution of AI in gene editing and precision medicine. As AI continues to develop, it is expected to play an increasingly important role in fields such as genomics, gene editing, and precision medicine, and provide more effective strategies for future disease treatment

VFL-Cafe: Communication-Efficient Vertical Federated Learning via Dynamic Caching and Feature Selection.

Vertical Federated Learning (VFL) is a promising category of Federated Learning that enables collaborative model training among distributed parties with data privacy protection. Due to its unique training architecture, a key challenge of VFL is high communication cost due to transmitting intermediate results between the Active Party and Passive Parties. Current communication-efficient VFL methods rely on using stale results without meticulous selection, which can impair model accuracy, particularly in noisy data environments. To address these limitations, this work proposes VFL-Cafe, a new VFL training method that leverages dynamic caching and feature selection to boost communication efficiency and model accuracy. In each communication round, the employed caching scheme allows multiple batches of intermediate results to be cached and strategically reused by different parties, reducing the communication overhead while maintaining model accuracy. Additionally, to eliminate the negative impact of noisy features that may undermine the effectiveness of using stale results to reduce communication rounds and incur significant model degradation, a feature selection strategy is integrated into each round of local updates. Theoretical analysis is then conducted to provide guidance on cache configuration, optimizing performance. Finally, extensive experimental results validate VFL-Cafe's efficacy, demonstrating remarkable improvements in communication efficiency and model accuracy.

Distributed Data Privacy Protection via Collaborative Anomaly Detection

Current anomaly detection methods for charging stations primarily rely on centralized network architectures with federated learning frameworks. However, the rapid increase in the number of charging stations and the expanding scale of these networks impose significant communication traffic loads. Consequently, it is essential to explore the relationship between data aggregation among charging stations and the anomaly detection accuracy at individual stations. In this paper, we address efficient anomaly detection in charging stations and propose a distributed anomaly detection algorithm powered by federated learning. To be specific, we introduce a distributed privacy-preserving data aggregation scheme, where a Transformer model is adopted to effectively smooth abnormal data fluctuations, minimizing disruptions to network aggregation nodes. Furthermore, we develop a distributed federated learning framework incorporating an efficient parameter update method without requiring prior knowledge or a central node. Compared with some existing detection solutions, the proposed approach significantly reduces communication bandwidth requirements while maintaining anomaly detection accuracy and mitigating data isolation issues. Extensive experiments demonstrate that the proposed algorithm not only achieves high accuracy in detecting anomalies in electric vehicle charging stations but also ensures robust user data privacy protection.

EFFECTIVENESS OF MULTIFACTOR AUTHENTICATION TECHNOLOGY FOR PROTECTING STUDENT PRIVACY : A SYSTEMATIC LITERATURE REVIEW

Student privacy is a major concern in the digital era, especially with the increasing use of educational technologies such as Learning Management Systems (LMS) and IoT devices. Traditional authentication systems are considered inadequate in the face of complex security threats. Therefore, this study evaluates the effectiveness of Multi-Factor Authentication (MFA) in protecting student privacy in an educational environment. This study uses a Systematic Literature Review (SLR) design based on 86 relevant articles selected from Scopus indexed journals (2020–2024). The articles were analyzed thematically using PRISMA Flow Diagram to identify patterns, trends, and gaps related to MFA implementation. The findings show that MFA can improve student privacy protection by reducing the risk of data leaks by up to 80%, lowering unauthorized access, and increasing user trust. Key technologies include biometrics, OTP, and blockchain, which have proven to be effective in improving security. However, MFA implementation faces obstacles such as cost, system complexity, and biometric data privacy concerns. This research makes an important contribution to academic literature and educational data security practices. Recommendations for further research include the exploration of behavior-based authentication methods, studies on user perception, and the implementation of MFA in educational environments with limited infrastructure. The practical implications include strengthening technology security policies in educational institutions and educating users to raise awareness of the importance of data privacy protection. Keywords: Student privacy, Multi-Factor Authentication (MFA), Educational Data Security, Biometric Technology

A Review of Multi-Source Data Fusion and Analysis Algorithms in Smart City Construction: Facilitating Real Estate Management and Urban Optimization

In the context of the booming construction of smart cities, multi-source data fusion and analysis algorithms play a key role in optimizing real estate management and improving urban efficiency. In this review, we comprehensively and systematically review the relevant algorithms, covering the types, characteristics, fusion techniques, analysis algorithms, and their synergies of multi-source data. We found that multi-source data, including sensors, social media, citizen feedback, and GIS data, face challenges such as data quality and privacy security when being fused. Data fusion algorithms are diverse and have their own advantages and disadvantages. Data analysis algorithms help urban management in areas such as spatial analysis and deep learning. Algorithm collaboration can improve decision-making accuracy and efficiency and promote the rational allocation of urban resources. In the future, algorithm development will focus on data quality, real-time, deep mining, interdisciplinary research, privacy protection, and collaborative application expansion, providing strong support for the sustainable development of smart cities.

Federated multi-task Bayesian network learning in the presence of overlapping and distinct variables

Bayesian Network (BN) is a powerful tool for causal dependence relationship discoveries of multivariate data. This article proposes a federated multi-task learning framework for BNs with overlapping and distinct variables. First, an additive structural causal model is proposed to describe the nonparametric causal dependence structure for each client’s BN. Then by assuming different clients can have similar, yet not identical, causal dependence structures, a two-step federated multi-task learning framework is formulated for parameter learning of different clients, which can protect data privacy in the meanwhile. In the first step, each client updates its local BN parameters with its own data. In the second step, the central server updates global parameters. The two steps iterate until converge. Numerical studies and a case study of a three-phase flow facility data demonstrate the efficacy of our proposed method.

FedKD-CPI: Combining the federated knowledge distillation technique to accomplish synergistic compound-protein interaction prediction.

Compound-protein interaction (CPI) prediction is critical in the early stages of drug discovery, narrowing the search space for CPIs and reducing the cost and time required for traditional high-throughput screening. However, CPI-related data are usually distributed across different institutions and their sharing is restricted because of data privacy and intellectual property rights. Constructing a scheme that enhances multi-institutional collaboration to improve prediction accuracy while protecting data privacy is essential. To this end, we propose FedKD-CPI, the first framework based on federated knowledge distillation, to effectively facilitate multi-party CPI collaborative prediction and ensure data privacy and security. FedKD-CPI uses knowledge distillation technology to extract the updated knowledge of all client models and train the model on the server to achieve knowledge aggregation, which can effectively utilize the knowledge contained in public and private data. We evaluate FedKD-CPI on three benchmark datasets and compare it with four baselines. The results show that FedKD-CPI is very close to centralized learning and significantly better than localized learning. Furthermore, FedKD-CPI outperforms federated learning-based baselines on independent and identically distributed data and non-independent and identically distributed data. Overall, FedKD-CPI improves the CPI prediction while ensuring data security and promoting institutions' collaboration to accelerate drug discovery.

Advanced Security Measures for Virtualized Data Storage: A Comprehensive Study

With the widespread application of virtualization technology in data centers, the security issues of data storage have become increasingly prominent. This paper aims to explore the application of information security in virtualized data storage to address the increasingly complex security challenges. The article first reviews the development of virtualization technology and the key technologies of virtualized data storage, then analyzes the current state and threats faced by information security in virtualized environments. Based on this, the paper discusses security requirements such as data integrity, access control, and privacy protection in detail, and delves into the application of information security technologies such as data encryption, intrusion detection and defense systems, security information and event management, and virtualization security policy management. Furthermore, this paper proposes a comprehensive security framework for virtualized data storage and describes its design principles, component architecture, and implementation deployment strategies in detail. Through experimental design and case studies, the paper validates the effectiveness of the proposed framework and evaluates its performance. Finally, the paper summarizes the research findings and proposes prospects for future research directions. This study not only provides theoretical support and practical guidance for information security in virtualized data storage but also offers valuable references for researchers and practitioners in related fields.

Application of blockchain technology in student learning data security and privacy protection

Application of blockchain technology in student learning data security and privacy protection

Application of federated learning in predicting breast cancer

The prediction and diagnosis of breast cancer relies on multimodal data, such as imaging, genetic information, and patient lifestyle habits. Federated learning provides a framework to protect data privacy, allowing multiple institutions to share model training without sharing the original data. This paper proposes a breast cancer prediction model combined with federated learning, where each participant trains the model locally using multimodal data such as imaging, genes, and treatment history. During the local training process, the data is normalized and feature extracted, initially classified using support vector machines (SVM) or penalized logistic regression and optimized using stochastic gradient descent (SGD). Subsequently, each participant then sends the updated model parameters to the central server, where the FedAvg algorithm combines them to produce a global model. The model achieves data protection, also accurately predicts the progression and recurrence risk of breast cancer. Although federated learning effectively solves the privacy protection problem, the issues of data heterogeneity and model interpretability still need to be addressed. In the future, interpretability technologies (such as SHAP and LIME) and transfer learning can be combined to improve the transparency and adaptability of the model.

Enhancing Smart Grid Security Using BLS Privacy Blockchain With Siamese Bi‐LSTM for Electricity Theft Detection

ABSTRACTEnergy management inside a blockchain framework developed for smart grids is primarily concerned with improving intrusion detection to protect data privacy. The emphasis is on real‐time detection of cyberattacks and preemptive forecasting of possible risks, especially in the realm of electricity theft within smart grid systems. Existing Electricity Theft Detection techniques for smart grids have obstacles such as class imbalance, which leads to poor generalization, increased complexity due to large EC data aspects, and a high false positive rate in supervised models, resulting in incorrect classification of regular customers as abnormal. To provide security in the smart grid, a novel BLS Privacy Blockchain with Siamese Bi‐LSTM is proposed. Initially, the privacy‐preserving Boneh‐Lynn‐Shacham blockchain technique is built on BLS Short signature and hash algorithms, which mitigate misclassification rates and false positives in the detection of smart grid attacks. Then, a hybrid framework employs an intrusion detection algorithm based on Siamese Bidirectional Long Short‐Term Memory to semantically distinguish between harmful and authentic behaviors, thereby improving data quality and predictive capabilities. Furthermore, a Recurrent Neural Network‐Generative Adversarial Network is presented for detecting electricity fraud, which addresses the issue of class imbalance. This uses both supervised and unsupervised loss functions to produce synthetic theft samples that closely resemble actual theft incidents. From the experiment, it is showing that the proposed models perform with high accuracy and low error rates. The proposed model from the outcomes when compared to other existing models achieves high accuracy, detection rate, recall, and low computation time.

Federated learning meets Bayesian neural network: Robust and uncertainty-aware distributed variational inference.

Federated Learning (FL) is a popular framework for data privacy protection in distributed machine learning. However, current FL faces some several problems and challenges, including the limited amount of client data and data heterogeneity. These lead to models trained on clients prone to drifting and overfitting, such that we just obtain suboptimal performance of the aggregated model. To tackle the aforementioned problems, we introduce a novel approach explicitly integrating Bayesian neural networks (BNNs) into the FL framework. The proposed approach is able to enhance the robustness. We refer to this approach as FedUAB, standing for FL with uncertainty-aware BNNs. In the FedUAB algorithm, each FL client independently trains a BNN using the Bayes by backprop algorithm. The weights of approximating model are modeled as Gaussian distributions, which mitigates the overfitting issue and also ensures better data privacy. Besides, we apply novel methods to overcome other key challenges in the fusion of BNNs and FL, such as selecting an optimal prior distribution, aggregating weights characterized by Gaussian forms across multiple clients, and rigorously managing weights variances. In the simulation of a FL environment, FedUAB demonstrated superior performance with both its server-side global model and client-side personalized models, outperforming traditional FL and other Bayesian FL methods. Moreover, it possesses the capability to quantify and decompose uncertainties. We have open-sourced our project at https://github.com/lpf111222/FedUAB/.

Data Privacy Protection Diagnostic Algorithm for Industrial Robot Joint Harmonic Reducers Based on Swarm Learning

Data Privacy Protection Diagnostic Algorithm for Industrial Robot Joint Harmonic Reducers Based on Swarm Learning

FinTech privacy security and customer engagement in Nigerian financial sector

One of the key achievements of digitization is the emergence of finance resources that could manage massive customer needs in the financial sector and tagged ‘Fintech’ the proliferation of this technology has become commonplace; creating plausible value addition in service delivery; as well as privacy concern on the technology effect on customer personal security/privacy information. The objective of this study is to examine fin-tech privacy security and customer engagement in Nigerian Financial Sector. Key issues to be considered include: customer privacy data protection, user application policy reforms, and customer trust. The Technology Acceptance Model (TAM) was adopted as the theoretical basis for articulating the model used for the study. Descriptive research design was adopted, in which 357questionnairs was administered to respondents in Lagos, Nigeria. The respondents were bank customers selected from the 2023 top five most profitable banks in Nigeria. systematic random sampling technique was adopted in selecting the respondents, which were administered based on the ranked percentages, additionally, personal interview was conducted to obtain information on where the close ended questionnaire could not cover. Data obtained was collated and analyzed. The study findings revealed that consistent breaches in customer privacy data, affect customers trust in Fintech, and the need to augment existing efforts in finding solutions to customer understanding of fintech application. The study recommends massive application of digital solutions by customers and service providers; as a means of countering the ‘gloomy side’ of fin-tech