Search

This paper highlights the importance of involving academic librarians in the development of ethical AI policies. The Academic Librarian Framework for Ethical AI Policy Development (ALF Framework) is introduced, recognizing librarians' unique skills and expertise. The paper discusses the benefits of their involvement, including expertise in information ethics and privacy, practical experience with AI tools, and collaborations. It also addresses challenges, such as limited awareness, institutional resistance, resource constraints, interdisciplinary collaboration, and evolving AI technologies, offering practical solutions. By actively involving librarians, institutions can develop comprehensive and ethical AI policies that prioritize social responsibility and respect for human rights. [ABSTRACT FROM AUTHOR]

Public libraries are an invaluable institution in the United States, and the digital revolution has posed many challenges for them. With the American Library Association's updated "Library Bill of Rights" and public library services increasingly moving online in response to the COVID-19 pandemic, the protection of patron privacy in public libraries is an important and timely topic of study. However, there is a lack of empirical data regarding privacy practices and the challenges that public libraries face. To fill this gap, we conducted an online survey that was sent to more than 12,500 public librarians across the country to study the state of patron privacy practices and challenges in public libraries. This study is the first of its kind on this topic. Our results show that patron privacy protections vary drastically depending on the library's size and service area. This study provides essential knowledge for administrators and policy makers in public libraries. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to validate two domain-specific information privacy competency models (IPCMs); the first for online consumers and the second for users of mobile applications (apps). For the validation of the competency models, we conducted qualitative research, using interviews to collect feedback by a group of nine information privacy experts. Regarding the evaluation, the experts commented largely positively for the structure and content of the IPCMs, as well as for the extent to which they achieve the intended goals. They also provided several points for improvements, which resulted in enhancing the quality of both IPCMs. The validation of the domain-specific demonstrated that this is the first study to empirically examine the privacy competencies that users of specific technological contexts should hold. The IPCMs can be used not only by educators and privacy policy makers for the design of privacy interventions, but also by e-commerce and mobile-apps providers, who could gain important insights into the way that they can be more reliable for their users. Both consumers and users of mobile-apps could benefit from IPCMs by acquiring the necessary privacy competencies through training programs for the protection of their information privacy. [ABSTRACT FROM AUTHOR]

With the increasing popularity of machine learning (ML) in image processing, privacy concerns have emerged as a significant issue in deploying and using ML services. However, current privacy protection approaches often require computationally expensive training from scratch or extensive fine-tuning of models, posing significant barriers to the development of privacy-conscious models, particularly for smaller organizations seeking to comply with data privacy laws. In this paper, we address the privacy challenges in computer vision by investigating the effectiveness of two recent fine-tuning methods, Model Reprogramming and Low-Rank Adaptation. We adapt these techniques to provide attribute protection for pre-trained models, minimizing computational overhead and training time. Specifically, we modify the models to produce privacy-preserving latent representations of images that cannot be used to identify unintended attributes. We integrate these methods into an adversarial min–max framework, allowing us to conceal sensitive information from feature outputs without extensive modifications to the pre-trained model, but rather focusing on a small set of new parameters. We demonstrate the effectiveness of our methods by conducting experiments on the CelebA dataset, achieving state-of-the-art performance while significantly reducing computational complexity and cost. Our research provides a valuable contribution to the field of computer vision and privacy, offering practical solutions to enhance the privacy of machine learning services without compromising efficiency. [ABSTRACT FROM AUTHOR]

In modern healthcare systems, data sources are highly integrated, and the privacy challenges are becoming a paramount concern. Despite the critical importance of privacy preservation in safeguarding sensitive and private information across various domains, there is a notable deficiency of learning and training material for privacy preservation. In this research, we present a k-anonymity algorithm explicitly for educational purposes. The development of the k-anonymity algorithm is complemented by seven validation tests, that have also been used as a basis for constructing five learning scenarios on privacy preservation. The outcomes of this research provide a practical understanding of a well-known privacy preservation technique and extends the familiarity of k-anonymity and the fundamental concepts of privacy protection to a broader audience. [ABSTRACT FROM AUTHOR]

Artificial intelligence-based algorithms are widely adopted in critical applications such as healthcare and autonomous vehicles. Mitigating the security and privacy issues of AI models, and enhancing their trustworthiness have become of paramount importance. We present a detailed investigation of existing security, privacy, and defense techniques and strategies to make machine learning more secure and trustworthy. We focus on the new paradigm of machine learning called federated learning, where one aims to develop machine learning models involving different partners (data sources) that do not need to share data and information with each other. In particular, we discuss how federated learning bridges security and privacy, how it guarantees privacy requirements of AI applications, and then highlight challenges that need to be addressed in the future. Finally, after having surveyed the high-level concepts of trustworthy AI and its different components and identifying present research trends addressing security, privacy, and trustworthiness separately, we discuss possible interconnections and dependencies between these three fields. All in all, we provide some insight to explain how AI researchers should focus on building a unified solution combining security, privacy, and trustworthy AI in the future. [ABSTRACT FROM AUTHOR]

Healthcare 4.0 is about collecting huge amounts of data and getting it to work in applications, enabling healthcare management decisions well‐informed while providing for important gains in effectiveness and cost control. Diagnostics based on the digital footprint depend on wearable technology's ability to gather and extract essential patient data. Artificial intelligence (AI) technologies allow the analysis of real‐time observed data and continuously developing from data to understand the world surrounding them. To connect and access intelligent healthcare services, people, and devices at any time, a secure wireless mobile communication system is essential. This article suggests a mHealth‐based patient monitoring system (mHealth‐PMS) based on AI for healthcare 4.0. Mobile healthcare applications motorized by Convolutional Neural Network (CNN) have enabled people to triage their conditions and preemptive treatment decisions. Information collected has been analysed for substantiating cause, and alert and preventive messages have been immediately sent through the mobile application. The performance analysis has been executed, and the proposed mobile application‐based surveillance provided much‐enhanced reporting of information quickly on diseases, symptoms, factors, and more. The mHealth‐PMS strategy shows an accuracy ratio of 95.6%, monitoring ratio of 93.5%, data management ratio of 94.4%, data security ratio of 91.7%, data privacy ratio of 92.1%, prediction ratio of 95.3%, a cost‐effective ratio of 25.5% compared to the existing methods. [ABSTRACT FROM AUTHOR]

Data sharing barriers present paramount challenges arising from multicenter clinical studies where multiple data sources are stored and managed in a distributed fashion at different local study sites. Merging such data sources into a common data storage for a centralized statistical analysis requires a data use agreement, which is often time‐consuming. Data merging may become more burdensome when propensity score modeling is involved in the analysis because combining many confounding variables, and systematic incorporation of this additional modeling in a meta‐analysis has not been thoroughly investigated in the literature. Motivated from a multicenter clinical trial of basal insulin treatment for reducing the risk of post‐transplantation diabetes mellitus, we propose a new inference framework that avoids the merging of subject‐level raw data from multiple sites at a centralized facility but needs only the sharing of summary statistics. Unlike the architecture of federated learning, the proposed collaborative inference does not need a center site to combine local results and thus enjoys maximal protection of data privacy and minimal sensitivity to unbalanced data distributions across data sources. We show theoretically and numerically that the new distributed inference approach has little loss of statistical power compared to the centralized method that requires merging the entire data. We present large‐sample properties and algorithms for the proposed method. We illustrate its performance by simulation experiments and the motivating example on the differential average treatment effect of basal insulin to lower risk of diabetes among kidney‐transplant patients compared to the standard‐of‐care. [ABSTRACT FROM AUTHOR]

The convergence of hydrogen energy with artificial intelligence (AI) in smart infrastructure has significant potential to revolutionise the worldwide energy sector. This article thoroughly examines the progress, difficulties, and potential breakthroughs in the integration of AI technology with smart grids to enhance the use of hydrogen energy. The study focuses on utilising AI technologies such as deep learning and machine learning to optimise the processes of generating, distributing, and utilising energy. The discoveries stemming from this investigation facilitate prognostic maintenance, instantaneous decision-making, and effective demand-side management, augmenting the durability and eco-friendliness of energy systems. Nevertheless, this auspicious panorama is surrounded by significant obstacles. Significant issues develop regarding data privacy and security when sensitive information is sent over AI-powered grid systems. Interoperability difficulties necessitate standardising the communication protocols to enable smooth data flow. Additionally, further research is essential to tackle the technological limitations of AI in grid management. This article presents a forward-thinking viewpoint on the incorporation of AI-enhanced smart grid technologies, with a focus on future expectations. Autonomous energy management systems offer improved flexibility, proactive maintenance, and flexible energy distribution. Simultaneously, the combination of Edge AI and decentralisation facilitates the establishment of energy generating and storage facilities at local levels. This helps to make immediate decisions, minimises delays, and improves the durability of the power grid. The report emphasises the pivotal importance of governmental and regulatory factors in directing these advancements. The foundation for a safe and flexible power system is established by data privacy legislation, grid modernisation initiatives, and incentives for hydrogen energy. The essay promotes energy market reforms, technological neutrality, and measures that improve grid resilience as a means of achieving environmental sustainability. The integration of hydrogen energy into smart infrastructure is facilitated by AI, and strategic planning and collaborative design are crucial for achieving a resilient, sustainable, and efficient energy future. This article provides a strategic plan for efficiently handling complexities, leveraging advantageous situations, and collaboratively building an energy industry that is adaptable, productive, and environmentally aware. • Explore AI's role in optimising energy processes for enhanced grid resilience. • Address privacy, security, interoperability, and technical constraints as significant hurdles. • Envision autonomous energy management, edge AI, and decentralisation for adaptive, resilient grids. • Emphasise regulatory frameworks for data privacy, grid modernisation, and renewable energy adoption. [ABSTRACT FROM AUTHOR]

With the application of robotics in security monitoring, medical care, image analysis, and other high-privacy fields, vision sensor data in robotic operating systems (ROS) faces the challenge of enhancing secure storage and transmission. Recently, it has been proposed that the distributed advantages of blockchain be taken advantage of to improve the security of data in ROS. Still, it has limitations such as high latency and large resource consumption. To address these issues, this paper introduces PrivShieldROS, an extended robotic operating system developed by InterPlanetary File System (IPFS), blockchain, and HybridABEnc to enhance the confidentiality and security of vision sensor data in ROS. The system takes advantage of the decentralized nature of IPFS to enhance data availability and robustness while combining HybridABEnc for fine-grained access control. In addition, it ensures the security and confidentiality of the data distribution mechanism by using blockchain technology to store data content identifiers (CID) persistently. Finally, the effectiveness of this system is verified by three experiments. Compared with the state-of-the-art blockchain-extended ROS, PrivShieldROS shows improvements in key metrics. This paper has been partly submitted to IROS 2024. [ABSTRACT FROM AUTHOR]

Stress is a natural yet potentially harmful aspect of human life, necessitating effective management, particularly during overwhelming experiences. This paper presents a scoping review of personalized stress detection models using wearable technology. Employing the PRISMA-ScR framework for rigorous methodological structuring, we systematically analyzed literature from key databases including Scopus, IEEE Xplore, and PubMed. Our focus was on biosignals, AI methodologies, datasets, wearable devices, and real-world implementation challenges. The review presents an overview of stress and its biological mechanisms, details the methodology for the literature search, and synthesizes the findings. It shows that biosignals, especially EDA and PPG, are frequently utilized for stress detection and demonstrate potential reliability in multimodal settings. Evidence for a trend towards deep learning models was found, although the limited comparison with traditional methods calls for further research. Concerns arise regarding the representativeness of datasets and practical challenges in deploying wearable technologies, which include issues related to data quality and privacy. Future research should aim to develop comprehensive datasets and explore AI techniques that are not only accurate but also computationally efficient and user-centric, thereby closing the gap between theoretical models and practical applications to improve the effectiveness of stress detection systems in real scenarios. [ABSTRACT FROM AUTHOR]

Differential privacy has emerged as a practical technique for privacy-preserving deep learning. However, recent studies on privacy attacks have demonstrated vulnerabilities in the existing differential privacy implementations for deep models. While encryption-based methods offer robust security, their computational overheads are often prohibitive. To address these challenges, we propose a novel differential privacy-based image generation method. Our approach employs two distinct noise types: one makes the image unrecognizable to humans, preserving privacy during transmission, while the other maintains features essential for machine learning analysis. This allows the deep learning service to provide accurate results, without compromising data privacy. We demonstrate the feasibility of our method on the CIFAR100 dataset, which offers a realistic complexity for evaluation. [ABSTRACT FROM AUTHOR]

As the biological, biomarker-driven framework of Alzheimer's disease (AD) becomes formalized through revised, consensus clinical criteria, clinicians will confront more and more patients in the earliest, asymptomatic stages of disease. The language and diction used by practitioners to characterize these early patients, whether they are diagnosed with AD, and how their condition is documented in medical and legal records have important implications for both their care and their medical-legal status outside of the health system. Investigation is needed urgently to better understand clinicians' views and practices regarding early AD, as we adapt to new disease definitions in this unprecedented era of care. [ABSTRACT FROM AUTHOR]

This article describes a tangible interface for an e-coach, co-designed in four countries to meet older adults' needs and expectations. The aim of this device is to coach the user by giving recommendations, personalized tasks and to build empathy through vocal, visual, and physical interaction. Through our co-design process, we collected insights that helped identifying requirements for the physical design, the interaction design and the privacy and data control. In the first phase, we collected users' needs and expectations through several workshops. Requirements were then transformed into three design concepts that were rated and commented by our target users. The final design was implemented and tested in three countries. We discussed the results and the open challenges for the design of physical e-coaches for older adults. To encourage further developments in this field, we released the research outputs of this design process in an open-source repository. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a collaborative artificial intelligence (AI) approach that enables distributed training of AI models without data sharing, thereby promoting privacy by design. However, it is essential to acknowledge that FL only offers a partial solution to safeguard the confidentiality of AI and machine learning (ML) models. Unfortunately, many studies fail to report the results of privacy measurement when applying FL, mainly due to assumptions that privacy is implicitly achieved as FL is a privacy-by-design approach. This trend can also be attributed to the complexity of understanding privacy measurement metrics and methods. This paper presents a survey of privacy measurement in FL, aimed at evaluating its effectiveness in protecting the privacy of sensitive data during the training of AI and ML models. While FL is a promising approach for preserving privacy during model training, ensuring privacy is genuinely achieved in practice is crucial. By evaluating privacy measurement metrics and methods in FL, we can identify the gaps in existing approaches and propose new techniques to enhance FL's privacy. A comprehensive study investigating "privacy measurement and metrics" in FL is therefore required to support the field's growth. Our survey provides a critical analysis of the current state of privacy measurement in FL, identifies gaps in existing research, and offers insights into potential research directions. Moreover, this paper presents a case study that evaluates the effectiveness of various privacy techniques in a specific FL scenario. This case study serves as tangible evidence of the real-world implications of privacy measurements, providing insightful and practical guidelines for researchers and practitioners to optimize privacy preservation while balancing other crucial factors such as communication overhead and accuracy. Finally, our paper outlines a future roadmap for advancing privacy in FL, combining traditional techniques with innovative technologies such as quantum computing and Trusted Execution Environments to fortify data protection. [ABSTRACT FROM AUTHOR]

Distributed model training is made possible by federated learning on various computing nodes, and compute nodes can submit model updates individually while preserving data privacy and avoiding the need to share raw user data. Unmanned Aerial Vehicle (UAV)-assisted edge computing utilizes its advantages of greater coverage, decreased latency, flexible deployment, and adapting to network infrastructure to offer users better services. In the context of federated learning-based UAV-assisted mobile edge computing, UAVs are deployed over the user devices to perform the process of locally aggregating the parameter updates. For global aggregation, these updates are subsequently transmitted to the edge base station, resulting in the updated model parameters. However, the performance of federated learning can be greatly affected due to computational and energy consumption, user reluctance to engage in training, and differences in the amount and quality of data from users. Hence, this study presents a novel approach in the form of a bilateral auction-based incentive mechanism. The objective is to encourage user engagement in training by considering crucial elements such as the magnitude of their data, the quality of their data, and the expenses associated with their devices. The experimental findings demonstrate that, in comparison to the benchmark method, the algorithm suggested in this study can incentivize users possessing high-quality data to engage in training, hence enhancing the overall training accuracy of federated learning. [ABSTRACT FROM AUTHOR]

This correspondence examines how LLMs, such as ChatGPT, have an effect on academic neurosurgery. It emphasises the potential of LLMs in enhancing clinical decision-making, medical education, and surgical practice by providing real-time access to extensive medical literature and data analysis. Although this correspondence acknowledges the opportunities that come with the incorporation of LLMs, it also discusses challenges, such as data privacy, ethical considerations, and regulatory compliance. Additionally, recent studies have assessed the effectiveness of LLMs in perioperative patient communication and medical education, and stressed the need for cooperation between neurosurgeons, data scientists, and AI experts to address these challenges and fully exploit the potential of LLMs in improving patient care and outcomes in neurosurgery. Significance: • The profound impact of technological advancements, particularly LLMs on reshaping the landscape of medical education and clinical decision-making in neurosurgery, offers unprecedented access to information and aids in evidence-based practice. • Analysing the opportunities and challenges arising from incorporating LLMs into neurosurgical practice underscores the necessity of embracing and leveraging innovative technologies to enhance patient care, surgical outcomes, and medical education in neurosurgery. [ABSTRACT FROM AUTHOR]

The article concentrates on exploring the issue of privacy‐preserving sliding mode consensus of multi‐agent systems (MASs) with disturbance. An encryption and decryption algorithm has been proposed to address data security and privacy issues during data transmission. To optimize network resource allocation, a dynamic event‐triggering mechanism has been introduced, which reduces the number of encrypted data while saving the computation cost. The consensus performance based on the sliding mode control strategy is achieved when the reachability of the slide‐mode surface is guaranteed, and then the slide‐mode controller is developed. Finally, an empirical demonstration through a numerical example validates the efficacy of the proposed strategy. [ABSTRACT FROM AUTHOR]

Background: Rare disease registries (RDRs) are valuable tools for improving clinical care and advancing research. However, they often vary qualitatively, structurally, and operationally in ways that can determine their potential utility as a source of evidence to support decision-making regarding the approval and funding of new treatments for rare diseases. Objectives: The goal of this research project was to review the literature on rare disease registries and identify best practices to improve the quality of RDRs. Methods: In this scoping review, we searched MEDLINE and EMBASE as well as the websites of regulatory bodies and health technology assessment agencies from 2010 to April 2023 for literature offering guidance or recommendations to ensure, improve, or maintain quality RDRs. Results: The search yielded 1,175 unique references, of which 64 met the inclusion criteria. The characteristics of RDRs deemed to be relevant to their quality align with three main domains and several sub-domains considered to be best practices for quality RDRs: (1) governance (registry purpose and description; governance structure; stakeholder engagement; sustainability; ethics/legal/privacy; data governance; documentation; and training and support); (2) data (standardized disease classification; common data elements; data dictionary; data collection; data quality and assurance; and data analysis and reporting); and (3) information technology (IT) infrastructure (physical and virtual infrastructure; and software infrastructure guided by FAIR principles (Findability; Accessibility; Interoperability; and Reusability). Conclusions: Although RDRs face numerous challenges due to their small and dispersed populations, RDRs can generate quality data to support healthcare decision-making through the use of standards and principles on strong governance, quality data practices, and IT infrastructure. [ABSTRACT FROM AUTHOR]

The applications of process mining, which is a business process management technique, in the field of healthcare are increasing day by day. In process mining, it is possible to analyze the process for three main purposes: discovery of the process, compliance control and process improvement, based on event logs recorded in information systems. Transforming patient-based healthcare processes data into process and event-based event logs is the first step of a process mining project in order to apply process mining techniques to human-centered, distributed, complex and multidisciplinary healthcare processes and to improve the quality of health care services. The process model discovered in multi-perspective process mining is expanded from different perspectives such as control flow, organizational, data, time and function, and the discovered process becomes more understandable. In this study, and in order to apply multi-perspective process mining, a method is proposed to convert the healthcare processes data recorded in hospital information systems into event logs. Data transformation method consists of six steps: data collection and data privacy, data integration, data conversion, data preprocessing, feature selection and extraction, and multi-perspective process mining analysis. The proposed method was validated by a case study by transforming the surgery process data of a university hospital in Turkey into an event log. The process discovery algorithm was applied to the surgery process data of the case study and the actual process was discovered, and the applicability of the data transformation method was shown on the real data. With the guiding feature of the method for healthcare professionals, it is expected to contribute to the applications of multi-perspective process mining in the field of healthcare in Turkey. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and blockchain technology have emerged as increasingly prevalent and influential elements shaping global trends in Information and Communications Technology (ICT). Namely, the synergistic combination of blockchain and AI introduces beneficial, unique features with the potential to enhance the performance and efficiency of existing ICT systems. However, presently, the confluence of these two disruptive technologies remains in a rather nascent stage, undergoing continuous exploration and study. In this context, the work at hand offers insight regarding the most significant features of the AI and blockchain intersection. Sixteen outstanding, recent articles exploring the combination of AI and blockchain technology have been systematically selected and thoroughly investigated. From them, fourteen key features have been extracted, including data security and privacy, data encryption, data sharing, decentralized intelligent systems, efficiency, automated decision systems, collective decision making, scalability, system security, transparency, sustainability, device cooperation, and mining hardware design. Moreover, drawing upon the related literature stemming from major digital databases, we constructed a timeline of this technological convergence comprising three eras: emerging, convergence, and application. For the convergence era, we categorized the pertinent features into three primary groups: data manipulation, potential applicability to legacy systems, and hardware issues. For the application era, we elaborate on the impact of this technology fusion from the perspective of five distinct focus areas, from Internet of Things applications and cybersecurity, to finance, energy, and smart cities. This multifaceted, but succinct analysis is instrumental in delineating the timeline of AI and blockchain convergence and pinpointing the unique characteristics inherent in their integration. The paper culminates by highlighting the prevailing challenges and unresolved questions in blockchain and AI-based systems, thereby charting potential avenues for future scholarly inquiry. [ABSTRACT FROM AUTHOR]

With the continuous advancement of information technology, a growing number of works, including articles, paintings, and music, are being digitized. Digital content can be swiftly shared and disseminated via the Internet. However, it is also vulnerable to malicious plagiarism, which can seriously infringe upon the rights of creators and dampen their enthusiasm. To protect creators' rights and interests, a sophisticated method is necessary to authenticate digital intellectual property rights. Traditional authentication methods rely on centralized, trustworthy organizations that are susceptible to single points of failure. Additionally, these methods are prone to network attacks that can lead to data loss, tampering, or leakage. Moreover, the circulation of copyright information often lacks transparency and traceability in traditional systems, which leads to information asymmetry and prevents creators from controlling the use and protection of their personal information during the authentication process. Blockchain technology, with its decentralized, tamper-proof, and traceable attributes, addresses these issues perfectly. In blockchain technology, each node is a peer, ensuring the symmetry of information. However, the transparent feature of blockchains can lead to the leakage of user privacy data. Therefore, this study designs and implements an Ethereum blockchain-based intellectual property authentication scheme with privacy protection. Firstly, we propose a method that combines elliptic curve cryptography (ECC) encryption with digital signatures to achieve selective encryption of user personal information. Subsequently, an authentication algorithm based on Zero-Knowledge Succinct Non-Interactive Argument of Knowledge (zk-SNARK) is adopted to complete the authentication of intellectual property ownership while encrypting personal privacy data. Finally, we adopt the InterPlanetary File System (IPFS) to store large files, solving the problem of blockchain storage space limitations. [ABSTRACT FROM AUTHOR]

Privacy impact assessment (PIA) has attracted the attention of privacy watchdogs and researchers for decades. This study focuses on a risk model and risk identification method, which are two crucial elements of the risk identification step in the PIA process. As a preparatory work, this article reviews national and international organizations’ current templates and guidelines and finds that PIA guidance includes multiple domains but rarely provide a risk model or a systematic risk identification method. Based on the analysis, our study offers a risk model that can capture various privacy risk realization processes. It further proposes a combination of risk identification methods that correspond to the main target domains in the PIA and the proposed risk model. This combination consists of privacy principles of a given personal information or privacy rule to check compliance with the rule, and our suggested list of risk factors is useful in inductively finding potential risk scenarios that violate social expectations of privacy. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) like GPT‐4 and Claude are catalyzing transformation across medical research including rheumatology. This review examines their applications, highlighting the pivotal role of prompt engineering in effectively guiding LLMs. Key aspects explored include literature synthesis, data analysis, manuscript drafting, coding assistance, privacy considerations, and generative artificial intelligence integrations. While LLMs accelerate workflows, reliance without apt prompting jeopardizes accuracy. By methodically constructing prompts and gauging model outputs, researchers can maximize relevance and utility. Locally run open‐source models also offer data privacy protections. As LLMs permeate rheumatology research, developing expertise in strategic prompting and assessing model limitations is critical. With proper oversight, LLMs markedly boost scholarly productivity. [ABSTRACT FROM AUTHOR]

In the realm of federated learning (FL), the exchange of model data may inadvertently expose sensitive information of participants, leading to significant privacy concerns. Existing FL privacy-preserving techniques, such as differential privacy (DP) and secure multi-party computing (SMC), though offering viable solutions, face practical challenges including reduced performance and complex implementations. To overcome these hurdles, we propose a novel and pragmatic approach to privacy preservation in FL by employing localized federated updates (LF3PFL) aimed at enhancing the protection of participant data. Furthermore, this research refines the approach by incorporating cross-entropy optimization, carefully fine-tuning measurement, and improving information loss during the model training phase to enhance both model efficacy and data confidentiality. Our approach is theoretically supported and empirically validated through extensive simulations on three public datasets: CIFAR-10, Shakespeare, and MNIST. We evaluate its effectiveness by comparing training accuracy and privacy protection against state-of-the-art techniques. Our experiments, which involve five distinct local models (Simple-CNN, ModerateCNN, Lenet, VGG9, and Resnet18), provide a comprehensive assessment across a variety of scenarios. The results clearly demonstrate that LF3PFL not only maintains competitive training accuracies but also significantly improves privacy preservation, surpassing existing methods in practical applications. This balance between privacy and performance underscores the potential of localized federated updates as a key component in future FL privacy strategies, offering a scalable and effective solution to one of the most pressing challenges in FL. [ABSTRACT FROM AUTHOR]

Federated learning is an upcoming concept used widely in distributed machine learning. Federated learning (FL) allows a large number of users to learn a single machine learning model together while the training data is stored on individual user devices. Nonetheless, federated learning lessens threats to data privacy. Based on iterative model averaging, our study suggests a feasible technique for the federated learning of deep networks with improved security and privacy. We also undertake a thorough empirical evaluation while taking various FL frameworks and averaging algorithms into consideration. Secure multi party computation, secure aggregation, and differential privacy are implemented to improve the security and privacy in a federated learning environment. In spite of advancements, concerns over privacy remain in FL, as the weights or parameters of a trained model may reveal private information about the data used for training. Our work demonstrates that FL can be prone to label-flipping attack and a novel method to prevent label-flipping attack has been proposed. We compare standard federated model aggregation and optimization methods, FedAvg and FedProx using benchmark data sets. Experiments are implemented in two different FL frameworks - Flower and PySyft and the results are analyzed. Our experiments confirm that classification accuracy increases in FL framework over a centralized model and the model performance is better after adding all the security and privacy algorithms. Our work has proved that deep learning models perform well in FL and also is secure. [ABSTRACT FROM AUTHOR]

Close-range interpersonal interactions serve as a major channel for virus transmission, with higher infection risks indoors than outdoors. Thus, evaluating indoor infectious disease transmission risks is vital for effective epidemic prevention and control. However, collecting complete individual-level behavioral data faces challenges due to privacy concerns and data acquisition costs, impeding accurate indoor risk mapping. To address this, we propose an individual-centered, scenario-based simulation framework in this paper. This framework incorporates stepwise movement of agents to model crowd interactions in indoor spaces, enabling infection risk mapping through geographic scenario simulation. The simulation model's core components encompass the generation of indoor environments, formulation of individual behavior rules, establishment of human-environment interaction logic, and simulation of virus transmission processes. Additionally, we outline the implementation algorithm for this simulation model. Lastly, we employ a high-risk university canteen as a case study to demonstrate the model's capabilities in creating risk maps at different levels: spatial, spatiotemporal, and individual. The proposed framework achieves the construction and process simulation of multi-dimensional geographic scenarios at a microscale, introduces a behavior path model based on spatiotemporal cubes, and enhances the comprehensive analysis and mapping capabilities for indoor infectious disease risk, laying the foundation for precise prevention and control. [ABSTRACT FROM AUTHOR]

Microsampling has revolutionized pharmaceutical drug development and clinical research by reducing sample volume requirements, allowing sample collection at home or nontraditional sites, minimizing animal and patient burden, and enabling more flexible study designs. This perspective paper discusses the transformative impact of microsampling and patient‐centric sampling (PCS) techniques, emphasizing their advantages in drug development and clinical trials. We highlight the integration of liquid chromatography‐mass spectrometry (LC–MS) strategies for analyzing PCS samples, focusing on our research experience and a review of current literatures. The paper reviews commercially available PCS devices, their regulatory status, and their application in clinical trials, underscoring the benefits of PCS in expanding patient enrollment diversity and improving study designs. We also address the operational challenges of implementing PCS, including the need for bridging studies to ensure data comparability between traditional and microsampling methods, and the analytical challenges posed by PCS samples. The paper proposes future directions for PCS, including the development of global regulatory standards, technological advancements to enhance user experience, the increased concern of sustainability and patient data privacy, and the integration of PCS with other technologies for improved performance in drug development and clinical studies. By advancing microsampling and PCS techniques, we aim to foster patient‐centric approaches in pharmaceutical sciences, ultimately enhancing patient care and treatment efficacy. [ABSTRACT FROM AUTHOR]

Ensuring source location privacy is crucial for the security of underwater acoustic sensor networks amid the growing use of marine environmental monitoring. However, the traditional source location privacy scheme overlooks multi-attacker cooperation strategies and also has the problem of high communication overhead. This paper addresses the aforementioned limitations by proposing an underwater source location privacy protection scheme based on game theory under the scenario of multiple cooperating attackers (SLP-MACGT). First, a transformation method of a virtual coordinate system is proposed to conceal the real position of nodes to a certain extent. Second, through using the relay node selection strategy, the diversity of transmission paths is increased, passive attacks by adversaries are resisted, and the privacy of source nodes is protected. Additionally, a secure data transmission technique utilizing fountain codes is employed to resist active attacks by adversaries, ensuring data integrity and enhancing data transmission stability. Finally, Nash equilibrium could be achieved after the multi-round evolutionary game theory of source node and multiple attackers adopting their respective strategies. Simulation experiments and performance evaluation verify the effectiveness and reliability of SLP-MACGT regarding aspects of the packet forwarding success rate, security time, delay and energy consumption: the packet delivery rate average increases by 30%, security time is extended by at least 85%, and the delay is reduced by at least 90% compared with SSLP, PP-LSPP, and MRGSLP. [ABSTRACT FROM AUTHOR]

Biometric authentication plays a vital role in various everyday applications with increasing demands for reliability and security. However, the use of real biometric data for research raises privacy concerns and data scarcity issues. A promising approach using synthetic biometric data to address the resulting unbalanced representation and bias, as well as the limited availability of diverse datasets for the development and evaluation of biometric systems, has emerged. Methods for a parameterized generation of highly realistic synthetic data are emerging and the necessary quality metrics to prove that synthetic data can compare to real data are open research tasks. The generation of 3D synthetic face data using game engines' capabilities of generating varied realistic virtual characters is explored as a possible alternative for generating synthetic face data while maintaining reproducibility and ground truth, as opposed to other creation methods. While synthetic data offer several benefits, including improved resilience against data privacy concerns, the limitations and challenges associated with their usage are addressed. Our work shows concurrent behavior in comparing semi-synthetic data as a digital representation of a real identity with their real datasets. Despite slight asymmetrical performance in comparison with a larger database of real samples, a promising performance in face data authentication is shown, which lays the foundation for further investigations with digital avatars and the creation and analysis of fully synthetic data. Future directions for improving synthetic biometric data generation and their impact on advancing biometrics research are discussed. [ABSTRACT FROM AUTHOR]

Russia's war on Ukraine and the resulting energy crisis have painfully reminded Europe that it must urgently reduce its dependence on fossil fuels. For a sustainable, secure and affordable energy future, the coming years will require a massive scale-up of renewable energy across the EU and a tremendous effort by European businesses and households to cut their energy consumption. The use of data and digital solutions can play a pivotal role in bolstering these efforts. This has been recognised in the European Commission's EU Action Plan on digitalising the energy system of October 2022, the first comprehensive plan for a twin green and digital transition in the European energy sector. While this plan is undeniably commendable, it is just a start. To fully unlock the potential of digitalisation in the transition towards sustainable energy systems, built around the active participation of consumers, significant shares of renewables, energy savings, and efficient energy use, the EU and its member states need to: Accelerate work on a common European energy data space, characterised by interoperable data standards, effective incentives for data sharing and adequate data protection and privacy safeguards for consumers. Ensure that citizens possess the necessary digital skills and information to reap the full benefits of the twin transition in terms of consumer empowerment and access to affordable and clean energy. Put in place the necessary safeguards regarding cybersecurity of energy networks to ensure that digital transformation does not jeopardise the resilience of EU energy systems. Use financial tools to accelerate the deployment of digital solutions in the energy sector and equip existing networks with the necessary digital infrastructure. [ABSTRACT FROM AUTHOR]

The growing popularity of wearable health devices like fitness trackers and smartwatches enables continuous personal health monitoring but also raises significant privacy concerns due to the real‐time collection of sensitive data. Many users are unaware of vulnerabilities that could lead to unauthorized access or discrimination if health information is revealed without consent. However, even informed users may willingly share data despite understanding privacy risks. The recent implementation of the General Data Protection Regulation (GDPR) in the EU and states taking initiatives to regulate privacy shows growing regulatory efforts to address these threats. This paper evaluates the key privacy threats posed specifically by consumer wearable devices. It provides a focused analysis of how health data could be exploited or shared without users' knowledge and the security flaws that enable such risks. Potential solutions including improving protections, empowering user control, enhancing transparency, and strengthening regulations are examined. However, it is argued that effective change requires balancing privacy risks with health benefits while also considering human decision‐making behaviors. The paper concludes by proposing a multifaceted approach to enable informed choices about wearable health data. This article is categorized under:Application Areas > Health CareCommercial, Legal, and Ethical Issues > Fairness in Data MiningCommercial, Legal, and Ethical Issues > Legal Issues [ABSTRACT FROM AUTHOR]

Background:Telemedicine is viewed as a crucial tool for addressing the challenges of limited medical resources at health care facilities. However, its adoption in health care is not entirely realized due to perceived barriers. This systematic review outlines the critical facilitators and barriers that influence the implementation of telemedicine in the Indian health care system, observed at the infrastructural, sociocultural, regulatory, and financial levels, from the perspectives of health care providers, patients, patient caregivers, society, health organizations, and the government. Methods:This review complies with the current Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Protocols 2015. A total of 2,706 peer-reviewed studies published from December 2016 to September 2023 in the PubMed, Cochrane, Scopus, Web of Science, CINAHL, MEDLINE, and PsycInfo databases were considered for the title and abstract screening, after which 334 articles were chosen for the full-text review. In the end, 46 studies were selected for data synthesis. Results:Analysis of the literature revealed key barriers such as data privacy and security concerns, doctor and patient resistance to information and communications technology (ICT), infrastructure issues, and ICT training gaps. Facilitators included reduced health care delivery costs, enhanced patient access to health care in remote areas, and shorter patient wait times. The real-world experiences of Indian telemedicine practitioners and pioneers are also explored to complement literature-based perspectives on telemedicine implementation. Both stress the need for reliable internet connectivity, technological adoption, comprehensive ICT training, positive sociocultural attitudes, stringent data privacy measures, and viable business models as crucial for effective telemedicine adoption, with experts emphasizing practical adaptability alongside the literature-recognized facilitators. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) in omics analysis raises privacy threats to patients. Here, we briefly discuss risk factors to patient privacy in data sharing, model training, and release, as well as methods to safeguard and evaluate patient privacy in AI-driven omics methods. [ABSTRACT FROM AUTHOR]

Recently, several private and political cloud initiatives emerged in Europe. This paper demonstrates how the sociotechnical imaginaries of three European cloud projects reveal a performative coupling of innovation and political ideas of control, territoriality and sovereignty. I ascertain three elements of the concept of sociotechnical imaginaries (innovation, boundary making and material properties) guiding the empirical analysis. Taking technology in the making and its role in (geo)politics seriously, this paper shows how imaginaries shape and interact with current geostrategic and political developments in Europe. The analysis of Microsoft's cloud, Bundescloud and GAIA-X reveals that rising privacy and data security issues have been integrated into cloud imaginaries that traditionally highlight progress and innovation. More specifically, state actors and cloud providers link and sometimes merge allegedly opposing technological aspects of innovation and politicised ideas of control such as digital sovereignty. This shift constitutes a move towards erecting political borders and localising IT within a global infrastructure. [ABSTRACT FROM AUTHOR]

This study presents a novel approach for generating unique identities from multi‐modal biometric data using ensemble feature descriptors extracted from the consistent regions of fingerprint and iris images. The method employs prominent feature selection and discriminant vector generation to enhance intra‐class similarity and inter‐class separability. Finally, a novel quantization mechanism is used to generate a unique identity. This identity might be vulnerable to many attacks. A shielding mechanism is proposed to address this issue. Experimental results substantiate the method's efficacy, satisfying criteria for distinctiveness, randomness, revocability, and irreversibility. Security analyses showcase resilience against diverse attacks, establishing its applicability in forensic investigations, digital wallets, remote authentication, and other privacy‐focused applications. The confidential UID generation scheme ensures privacy and security without involving biometric data or UID enrollment, enhancing its suitability across various applications. [ABSTRACT FROM AUTHOR]

The federated learning has gained prominent attention as a collaborative machine learning method, allowing multiple users to jointly train a shared model without directly exchanging raw data. This research addresses the fundamental challenge of balancing data privacy and utility in distributed learning by introducing an innovative hybrid methodology fusing differential privacy with federated learning (HDP‐FL). Through meticulous experimentation on EMNIST and CIFAR‐10 data sets, this hybrid approach yields substantial advancements, showcasing a noteworthy 4.22% and up to 9.39% enhancement in model accuracy for EMNIST and CIFAR‐10, respectively, compared to conventional federated learning methods. Our adjustments to parameters highlighted how noise impacts privacy, showcasing the effectiveness of our hybrid DP approach in striking a balance between privacy and accuracy. Assessments across diverse FL techniques and client counts emphasized this trade‐off, particularly in non‐IID data settings, where our hybrid method effectively countered accuracy declines. Comparative analyses against standard machine learning and state‐of‐the‐art FL approaches consistently showcased the superiority of our proposed model, achieving impressive accuracies of 96.29% for EMNIST and 82.88% for CIFAR‐10. These insights offer a strategic approach to securely collaborate and share knowledge among IoT devices without compromising data privacy, ensuring efficient and reliable learning mechanisms across decentralized networks. [ABSTRACT FROM AUTHOR]

With the growing significance of Credit Risk Analysis (CRA) with a focus on privacy, there is a pressing demand for a Privacy Preserving Machine Learning (PPML) decision support system. In this context, we introduce a framework for privacy‐preserving credit risk analysis that utilizes Homomorphic Encryption aware Logistic Regression (HELR) on encrypted data. The implementation involves the use of TenSEAL and Torch libraries for Logistic Regression (LR), integrating the proposed HELR on polynomial degrees 3 and 5 across German, Taiwan, Japan, and Australian datasets. The presented model yields satisfactory results compared to non‐Homomorphic Encryption (HE) models, demonstrating a minimal accuracy difference ranging from 0.5% to 7.8%. Notably, HELR_g5 outperforms HELR_g3, exhibiting a higher Area Under Curve (AUC) value. Additionally, a thorough security analysis indicates the resilience of the proposed system against various privacy attacks, including poison attacks, evasion attacks, member inference attacks, model inversion attacks, and model extraction attacks at different stages of machine learning. Finally, in the comparative analysis, we highlight that the proposed model ensures data privacy, encompassing training privacy and model privacy during the training phase, as well as input and output privacy during the inference phase a level of privacy not achieved by existing systems. [ABSTRACT FROM AUTHOR]

Access control systems have become integral to every organization's defensive arsenal to protect sensitive information and ensure that businesses comply with data privacy regulations. The goal is to block out anyone who shouldn't be able to get their hands on sensitive information. Authorization solutions like access control help keep sensitive information safe by enforcing strict rules against unauthorized users. This study investigates the difficulties of pushback request response management in P2P electronic health records (EHRs) and suggests a blockchain-enabled EHR for a decentralized P2P healthcare facility. To prevent privacy breaches in the blockchain network and to make information more easily accessible, a new method of authentic access control has been created and implemented. The PRR is an innovative method proposed where security-based mathematical representation and modelling on EHR datasets create a proven security aspect of data privacy. We tested on-chain and off-chain computing modalities by implementing them. Simulations with our implementation show that our suggested pushback request response to medical data significantly lowers the overall peak request. The off-chain computing method offers lower delay time and overhead than the on-chain mode while maintaining the same level of system integrity. In addition, we evaluated the suggested method in terms of its performance and security, and we compared it to an existing hybrid method while taking into account data from the New York State Department of Health. [ABSTRACT FROM AUTHOR]

Biometric technology has various applications in smart healthcare systems, including patient authentication, health monitoring, telemedicine, clinical decision support, and personalized care. In addition, medical records contain sensitive and personal information, making them vulnerable to unauthorized access and theft. Because biometric data is distinct and unchangeable, unlike passwords or PINs, using biometric technologies in smart healthcare systems creates privacy problems. This creates privacy concerns as this information is highly sensitive and can be used to identify an individual, making it a valuable target for malicious actors. Subsequently, the storage and use of biometric data in smart healthcare systems must be handled with care to ensure that individuals' privacy rights are protected. Privacy by design is a concept that emphasizes the importance of incorporating privacy considerations into the design and development of products, services, and systems. In this paper, we presented different forms of biometric factors and technologies and their applications in the smart healthcare system to enhance security and privacy in relation to principles of privacy by design. In addition, the study analyzed a variety of attacks and techniques that can be utilized to compromise biometric technology in a smart healthcare system and presented some open research questions. [ABSTRACT FROM AUTHOR]

One of the main concerns of cloud-based services based on machine and deep learning algorithms is the privacy of users' data. This is particularly relevant when companies want to leverage such services because they have to outsource potentially sensible data to be processed. In this work, the problem of privacy-preserving anomaly detection on industrial vibrational data with machine learning is tackled. It consists in the detection of irregularities or deviations from expected patterns in the vibration signals generated by industrial machinery and equipment. Such anomalies can be indicative of potential equipment failures, maintenance needs, or process deviations, making their timely detection critical for ensuring the smooth operation and reliability of industrial systems. We combine this industrial need with the ability to guarantee data privacy by proposing encrypted vibrational anomaly detection (EVAD). EVAD allows the detection of anomalies on vibrational data in a privacy-preserving manner by integrating, for the first time in the literature, one-class support vector machines and homomorphic encryption, the latter being a particular kind of encryption that allows the computation of some operations directly on encrypted data. Experimental results show that, on two publicly available datasets for vibrational anomaly detection, EVAD is able to distinguish, in a privacy-preserving manner, between nominal and anomaly situations, in an effective and efficient way. To the best of our knowledge, EVAD represents the first privacy-preserving solution for the detection of anomalies in vibrational data present in the literature. [ABSTRACT FROM AUTHOR]

In recent years, credit card transaction fraud has resulted in massive losses for both consumers and banks. Subsequently, both cardholders and banks need a strong fraud detection system to reduce cardholder losses. Credit card fraud detection (CCFD) is an important method of fraud prevention. However, there are many challenges in developing an ideal fraud detection system for banks. First off, due to data security and privacy concerns, various banks and other financial institutions are typically not permitted to exchange their transaction datasets. These issues make traditional systems find it difficult to learn and detect fraud depictions. Therefore, this paper proposes federated learning for CCFD over different frameworks (TensorFlow federated, PyTorch). Second, there is a significant imbalance in credit card transactions across all banks, with a small percentage of fraudulent transactions outweighing the majority of valid ones. In order to demonstrate the urgent need for a comprehensive investigation of class imbalance management techniques to develop a powerful model to identify fraudulent transactions, the dataset must be balanced. In order to address the issue of class imbalance, this study also seeks to give a comparative analysis of several individual and hybrid resampling techniques. In several experimental studies, the effectiveness of various resampling techniques in combination with classification approaches has been compared. In this study, it is found that the hybrid resampling methods perform well for machine learning classification models compared to deep learning classification models. The experimental results show that the best accuracy for the Random Forest (RF); Logistic Regression; K-Nearest Neighbors (KNN); Decision Tree (DT), and Gaussian Naive Bayes (NB) classifiers are 99,99%; 94,61%; 99.96%; 99,98%, and 91,47%, respectively. The comparative results show that the RF outperforms with high performance parameters (accuracy, recall, precision and f score) better than NB; RF; DT and KNN. RF achieve the minimum loss values with all resampling techniques, and the results, when utilizing the proposed models on the entire skewed dataset, achieved preferable outcomes to the unbalanced dataset. Furthermore, the PyTorch framework achieves higher prediction accuracy for the federated learning model than the TensorFlow federated framework but with more computational time. [ABSTRACT FROM AUTHOR]