-
Sensors (Basel, Switzerland) Jan 2023Effective accident management acts as a vital part of emergency and traffic control systems. In such systems, accident data can be collected from different sources...
Effective accident management acts as a vital part of emergency and traffic control systems. In such systems, accident data can be collected from different sources (unmanned aerial vehicles, surveillance cameras, on-site people, etc.) and images are considered a major source. Accident site photos and measurements are the most important evidence. Attackers will steal data and breach personal privacy, causing untold costs. The massive number of images commonly employed poses a significant challenge to privacy preservation, and image encryption can be used to accomplish cloud storage and secure image transmission. Automated severity estimation using deep-learning (DL) models becomes essential for effective accident management. Therefore, this article presents a novel Privacy Preserving Image Encryption with Optimal Deep-Learning-based Accident Severity Classification (PPIE-ODLASC) method. The primary objective of the PPIE-ODLASC algorithm is to securely transmit the accident images and classify accident severity into different levels. In the presented PPIE-ODLASC technique, two major processes are involved, namely encryption and severity classification (i.e., high, medium, low, and normal). For accident image encryption, the multi-key homomorphic encryption () technique with lion swarm optimization (LSO)-based optimal key generation procedure is involved. In addition, the PPIE-ODLASC approach involves YOLO-v5 object detector to identify the region of interest (ROI) in the accident images. Moreover, the accident severity classification module encompasses Xception feature extractor, bidirectional gated recurrent unit (BiGRU) classification, and Bayesian optimization (BO)-based hyperparameter tuning. The experimental validation of the proposed PPIE-ODLASC algorithm is tested utilizing accident images and the outcomes are examined in terms of many measures. The comparative examination revealed that the PPIE-ODLASC technique showed an enhanced performance of 57.68 dB over other existing models.
Topics: Humans; Privacy; Bayes Theorem; Computer Security; Confidentiality; Machine Learning
PubMed: 36617116
DOI: 10.3390/s23010519 -
Sensors (Basel, Switzerland) Dec 2022Personal health records (PHR) represent health data managed by a specific individual. Traditional solutions rely on centralized architectures to store and distribute...
Personal health records (PHR) represent health data managed by a specific individual. Traditional solutions rely on centralized architectures to store and distribute PHR, which are more vulnerable to security breaches. To address such problems, distributed network technologies, including blockchain and distributed hash tables (DHT) are used for processing, storing, and sharing health records. Furthermore, fully homomorphic encryption (FHE) is a set of techniques that allows the calculation of encrypted data, which can help to protect personal privacy in data sharing. In this context, we propose an architectural model that applies a DHT technique called the interplanetary protocol file system and blockchain networks to store and distribute data and metadata separately; two new elements, called data steward and shared data vault, are introduced in this regard. These new modules are responsible for segregating responsibilities from health institutions and promoting end-to-end encryption; therefore, a person can manage data encryption and requests for data sharing in addition to restricting access to data for a predefined period. In addition to supporting calculations on encrypted data, our contribution can be summarized as follows: (i) mitigation of risk to personal privacy by reducing the use of unencrypted data, and (ii) improvement of semantic interoperability among health institutions by using distributed networks for standardized PHR. We evaluated performance and storage occupation using a database with 1.3 million COVID-19 registries, which showed that combining FHE with distributed networks could redefine e-health paradigms.
Topics: Humans; Blockchain; Electronic Health Records; Confidentiality; COVID-19; Computer Security; Health Records, Personal
PubMed: 36616613
DOI: 10.3390/s23010014 -
Healthcare (Basel, Switzerland) Dec 2022The public perceive social media as a convenient source of health information. Some physicians might use this to enhance their visibility and market value. In this...
The public perceive social media as a convenient source of health information. Some physicians might use this to enhance their visibility and market value. In this study, we aimed to assess medical students' awareness of regulations for dispersion of health-related information on social media and physicians' online self-promotional activities. A cross-sectional study was conducted among undergraduate medical students from the 3 largest administrative regions of Saudi Arabia: Central, Western, and Eastern regions. Data was collected between February-July 2020 via online distribution of a self-administered questionnaire. Results showed that: (a) a total of 730 medical students participated; (b) about half of respondents were unsure or unaware of guidelines of both, online posting of medical information and physicians' online self-promotional activities (343/47% and 385/52.7%, respectively); (c) 610 (83.6%) students supported that healthcare providers report accounts sharing unreliable health information. Physicians' online promotional activities, and posting about successful cases, might shift physicians' focus from patient care to becoming more popular online. Care should be taken not to breach essential professional and ethical principles, such as protecting the confidentiality and privacy of patients. Raising awareness among patients and physicians, current and future ones, of the regulations governing these online health related interactions is imperative.
PubMed: 36611481
DOI: 10.3390/healthcare11010021 -
Journal of Ambient Intelligence and... 2023In the present E-healthcare industry, data breaches result in substantial economic losses due to cyber-attacks and hence create a trust deficit between the industry and...
In the present E-healthcare industry, data breaches result in substantial economic losses due to cyber-attacks and hence create a trust deficit between the industry and users. The healthcare industry has rapidly adopted IoT frameworks but the trust deficit and privacy concerns limit its utilization among the masses. Along with privacy protection, content authentication is an important requirement in a number of critical applications and fragile watermarking provides an effective solution. However, existing fragile watermarking techniques lack the accuracy of tamper detection and hence are not reliable enough in terms of security and privacy of the data. This paper presents a novel low-complexity block-based fragile watermarking technique with high security against cyber-security attacks. This is achieved by embedding a fragile watermark in the host image using pixel domain blocking approach. The security of embedded watermark has been taken care of by using Cellular Automata and DNA based ENcryption (CADEN) framework to scramble the watermark bits using various secret keys. Experimental investigations show that besides being highly secure, the proposed technique is fragile to various signal processing and geometric attacks. The comparative analysis shows that the proposed scheme, despite having lower complexity, offers better efficiency in terms of imperceptibility, tamper detection and localization compared to other state-of-the-art techniques. Besides, the fragile watermark embedding makes the system capable to preserve the secret information in case of an attack with an average BER of 40%.
PubMed: 36590234
DOI: 10.1007/s12652-022-04510-8 -
The Journal of Privacy and... 2023With growing demand for data reuse and open data within the scientific ecosystem, protecting the confidentialy of survey data and privacy of data subjects is...
With growing demand for data reuse and open data within the scientific ecosystem, protecting the confidentialy of survey data and privacy of data subjects is increasingly important. Doing so requires more than legal procedures and technological controls; it requires social and behavioral intervention. In this research note, we delineate the disclosure risks of various types of survey data (e.g., longitudinal data, social network data, sensitive information, biomarkers, and geographic data), the current motivation for data reuse, and challenges to data protection. Despite rigorous efforts to protect data, there are still threats to protection of confidentiality in microdata. Unintentional data breaches, protocol violations, and data misuse are observed even in well-established restricted data access systems, indicating that the systems may all rely heavily on trust. Creating and maintaining that trust is critical to secure data access. We suggest four ways of building trust; with an example of a new project '' by the Inter-university Consortium for Political and Social Research. Continuous user-focused improvements in restricted data access systems are necessary so that we promote a culture of trust among the research and data user community, train both in the general topic of responsible research and in the specific requirements of these systems, and offer systematic and holistic solutions.
PubMed: 38550525
DOI: 10.29012/jpc.845 -
PloS One 2022Maintaining patient privacy when geocoding and linking residential address information with neighborhood-level data can create challenges during research. Challenges may...
Characterizing the neighborhood risk environment in multisite clinic-based cohort studies: A practical geocoding and data linkages protocol for protected health information.
BACKGROUND
Maintaining patient privacy when geocoding and linking residential address information with neighborhood-level data can create challenges during research. Challenges may arise when study staff have limited training in geocoding and linking data, or when non-study staff with appropriate expertise have limited availability, are unfamiliar with a study's population or objectives, or are not affordable for the study team. Opportunities for data breaches may also arise when working with non-study staff who are not on-site. We detail a free, user-friendly protocol for constructing indices of the neighborhood risk environment during multisite, clinic-based cohort studies that rely on participants' protected health information. This protocol can be implemented by study staff who do not have prior training in Geographic Information Systems (GIS) and can help minimize the operational costs of integrating geographic data into public health projects.
METHODS
This protocol demonstrates how to: (1) securely geocode patients' residential addresses in a clinic setting and match geocoded addresses to census tracts using Geographic Information System software (Esri, Redlands, CA); (2) ascertain contextual variables of the risk environment from the American Community Survey and ArcGIS Business Analyst (Esri, Redlands, CA); (3) use geoidentifiers to link neighborhood risk data to census tracts containing geocoded addresses; and (4) assign randomly generated identifiers to census tracts and strip census tracts of their geoidentifiers to maintain patient confidentiality.
RESULTS
Completion of this protocol generates three neighborhood risk indices (i.e., Neighborhood Disadvantage Index, Murder Rate Index, and Assault Rate Index) for patients' coded census tract locations.
CONCLUSIONS
This protocol can be used by research personnel without prior GIS experience to easily create objective indices of the neighborhood risk environment while upholding patient confidentiality. Future studies can adapt this protocol to fit their specific patient populations and analytic objectives.
Topics: Humans; Geographic Mapping; Geographic Information Systems; Public Health; Cohort Studies; Residence Characteristics
PubMed: 36580446
DOI: 10.1371/journal.pone.0278672 -
Computers & Education Dec 2021Online teaching has been implemented in response to the COVID-19 pandemic. Nonetheless, teaching online consumes considerable time and adds pressure to teachers' daily...
Online teaching has been implemented in response to the COVID-19 pandemic. Nonetheless, teaching online consumes considerable time and adds pressure to teachers' daily lives. Teachers have to not only acquire technical skills but also provide engaging instruction online. Meanwhile, privacy breaches occasionally occur in online teaching. The objective of the current study is to analyze the factors underlying the continuance intention toward online teaching beyond the COVID-19 pandemic. We use the person-environment fit theory to develop the survey for investigation. An open-ended question appended to the survey helps to gather teachers' further thoughts on sustainable online teaching. The structural equation modeling reveals that teachers' technostress is associated with their privacy concerns and self-efficacy in delivering effective instruction amid online teaching. The multigroup analysis further demonstrates that technostress, self-efficacy and school support are related to the continuance intention to teach online for teachers at distinct teaching levels to different extents. The responses to the open-ended question reveal that teachers' preference for online instruction lies in wealthy teaching resources and flexibility. Students' learning performance and the effectiveness of assessments constitute a concern in conducting online teaching. The implications for policymakers and teachers are remarked upon at the end of this paper.
PubMed: 36569235
DOI: 10.1016/j.compedu.2021.104335 -
Pacific Symposium on Biocomputing.... 2023Federated learning is becoming increasingly more popular as the concern of privacy breaches rises across disciplines including the biological and biomedical fields. The...
Federated learning is becoming increasingly more popular as the concern of privacy breaches rises across disciplines including the biological and biomedical fields. The main idea is to train models locally on each server using data that are only available to that server and aggregate the model (not data) information at the global level. While federated learning has made significant advancements for machine learning methods such as deep neural networks, to the best of our knowledge, its development in sparse Bayesian models is still lacking. Sparse Bayesian models are highly interpretable with natural uncertain quantification, a desirable property for many scientific problems. However, without a federated learning algorithm, their applicability to sensitive biological/biomedical data from multiple sources is limited. Therefore, to fill this gap in the literature, we propose a new Bayesian federated learning framework that is capable of pooling information from different data sources without breaching privacy. The proposed method is conceptually simple to understand and implement, accommodates sampling heterogeneity (i.e., non-iid observations) across data sources, and allows for principled uncertainty quantification. We illustrate the proposed framework with three concrete sparse Bayesian models, namely, sparse regression, Markov random field, and directed graphical models. The application of these three models is demonstrated through three real data examples including a multi-hospital COVID-19 study, breast cancer protein-protein interaction networks, and gene regulatory networks.
Topics: Humans; Electronic Health Records; Bayes Theorem; COVID-19; Computational Biology; Genomics
PubMed: 36541002
DOI: No ID Found -
Computer Communications Feb 2023COVID-19 data analysis and prediction from patient data repository collected from hospitals and health organizations. Users' credentials and personal information are at...
COVID-19 data analysis and prediction from patient data repository collected from hospitals and health organizations. Users' credentials and personal information are at risk; it could be an unrecoverable issue worldwide. A Homomorphic identification of possible breaches could be more appropriate for minimizing the risk factors in preventing personal data. Individual user privacy preservation is a must-needed research focus in various fields. Health data generated and collected information from multiple scenarios increasing the complexity involved in maintaining secret patient information. A homomorphic-based systematic approach with a deep learning process could reduce depicts and illegal functionality of unknown organizations trying to have relation to the environment and physical and social relations. This article addresses the homomorphic standard system functionality, which refers to all the functional aspects of deep learning system requirements in COVID-19 health management. Moreover, this paper spotlights the metric privacy incorporation for improving the Deep Learning System (DPLS) approaches for solving the healthcare system's complex issues. It is absorbed from the result analysis Homomorphic-based privacy observation metric gradually improves the effectiveness of the deep learning process in COVID-19-health care management.
PubMed: 36531214
DOI: 10.1016/j.comcom.2022.12.004 -
Sensors (Basel, Switzerland) Nov 2022Smart cities assure the masses a higher quality of life through digital interconnectivity, leading to increased efficiency and accessibility in cities. In addition, a...
Smart cities assure the masses a higher quality of life through digital interconnectivity, leading to increased efficiency and accessibility in cities. In addition, a huge amount of data is being exchanged through smart devices, networks, cloud infrastructure, big data analysis and Internet of Things (IoT) applications in the various private and public sectors, such as critical infrastructures, financial sectors, healthcare, and Small and Medium Enterprises (SMEs). However, these sectors require maintaining certain security mechanisms to ensure the confidentiality and integrity of personal and critical information. However, unfortunately, organizations fail to maintain their security posture in terms of security mechanisms and controls, which leads to data breach incidents either intentionally or inadvertently due to the vulnerabilities in their information management systems that either malicious insiders or attackers exploit. In this paper, we highlight the importance of data breaches and issues related to information leakage incidents. In particular, the impact of data breaching incidents and the reasons contributing to such incidents affect the citizens' well-being. In addition, this paper also discusses various preventive measures such as security mechanisms, laws, standards, procedures, and best practices, including follow-up mitigation strategies.
Topics: Quality of Life; Computer Security; Privacy; Confidentiality; Internet of Things
PubMed: 36502039
DOI: 10.3390/s22239338