• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.958-979
• /
• 2023

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

• Asia pacific journal of information systems
• /
• v.27 no.3
• /
• pp.156-175
• /
• 2017

The proposed conceptual framework is based in the relationships among knowledge of personal information security, trust on the personal information security policies of parcel delivery service companies, privacy concern, trust in and risk of parcel delivery services, and user satisfaction with parcel delivery services. Drawing upon both cognitive theory of emotion and cognitive emotion theory that complement each other, we propose a research model and examine the relationships between cognitive and emotional factors and the usage of parcel delivery services. The proposed model is validated using data from customers who have previously used parcel delivery services. The results show a significant relationship between the cognitive and affective factors and the usage of parcel delivery services. This study enhances our understanding of parcel delivery services based on the consumers' psychological processes and presents useful implications on the importance of privacy and security in these services.

• Journal of the Korean housing association
• /
• v.18 no.2
• /
• pp.11-20
• /
• 2007

The purpose of this study is to find the apartment Choice and Housing Satisfaction by the Housing Value Segmentation. Survey questionnaires were conducted on 1103 married women from three residential areas in Daegu. Data were analized by SPSS package program. Major findings are the following: Quality oriented type preferred environment oriented and multiple apartment. Safety investment type answered the bases of the information as of sales/model house, real estate office, oral information from relative neighbor. Ostentation negative type is dissatisfied for the present apartment were listed such as inconvenient inner structure and inner space, education environment for children, privacy protection, convenient transportation for the urban area. Convenience educational environment type is dissatisfied for the present apartment were listed such as inconvenient inner structure and inner space, anti sonic materials, education environment for children, privacy protection.

• Knowledge Management Research
• /
• v.24 no.1
• /
• pp.51-72
• /
• 2023

Digital literacy is vital knowledge and ability of an individual in the information society. As the level of digital literacy increases, the interest in privacy protection increases. This change may hinder the use of digital technologies and services. This research examines (1) the mediating effect of online social participation and information veracity on smart device literacy and privacy concerns, and (2) the moderating effect of privacy literacy. Using Korean media panel survey data reported in 2020 and in 2021, this study analyzes the responses of 7,737 people who use smart devices and participate in online activities. SPSS and PROCESS Macro are used to test the research model and hypotheses. In the analysis of 2020 and 2021 survey, this research shows that smart device literacy has major effects on privacy concerns; confirms that the mediating effect of online social participation; moderated meditating effect of privacy literacy. Although information veracity is not significant in 2020, mediating and moderated mediating effects are found in 2021.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.735-741
• /
• 1997

In the present paper, we propose a new randomization device free mail survey method. The estimator based on proposed model is unbiased and more efficient than the estimator based on SIngh, Mangat and Singh model (SMS-model)(1993) when $\pi$<1/2, and more protective than SMS-model in view of the protection of privacy regardless of the values of $\pi$ and $\pi_Y$ only if we count the number of say 'Yes' from the respondents. However, If we consider the respondents that say 'No', the SMS-model is more protective than our model.

• Journal of Digital Convergence
• /
• v.17 no.7
• /
• pp.285-292
• /
• 2019

With the popularization of PC, SNS and IoT, a lot of data is generated and the amount is increasing exponentially. Artificial neural network learning is a topic that attracts attention in many fields in recent years by using huge amounts of data. Artificial neural network learning has shown tremendous potential in speech recognition and image recognition, and is widely applied to a variety of complex areas such as medical diagnosis, artificial intelligence games, and face recognition. The results of artificial neural networks are accurate enough to surpass real human beings. Despite these many advantages, privacy problems still exist in artificial neural network learning. Learning data for artificial neural network learning includes various information including personal sensitive information, so that privacy can be exposed due to malicious attackers. There is a privacy risk that occurs when an attacker interferes with learning and degrades learning or attacks a model that has completed learning. In this paper, we analyze the attack method of the recently proposed neural network model and its privacy protection method.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.115-120
• /
• 2015

As the cloud services, the underlying technology of the digital convergence environment, have been widely adopted in the business, personal information protection has been recognized as one of the major issues to resolve. When cloud services are used to process the personal information, the personal information protection law speculates the establishment of a contract or service level agreement(SLA). This research presents 7 privacy indicators and 13 metrics which can be included in cloud SLA, based on the analysis of related regulation and standards and the SMART(Specific, Measurable, Action-oriented, Relevant and Timely) model. The proposed indicators are examined using the Focus Group Interview method in terms of materiality and feasibility. The results show that all the proposed indicators are meaningful and useful.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.275-281
• /
• 2015

The recent health care is growing rapidly want to receive offers users a variety of medical services, can be exploited easily exposed to a third party information on the role of the patient's hospital staff (doctors, nurses, pharmacists, etc.) depending on the patient clearly may have to be classified. In this paper, in order to ensure safe use by third parties in the health care environment, classify the attributes of patient information and patient privacy protection technique using hierarchical multi-property rights proposed to classify information according to the role of patient hospital officials The. Hospital patients and to prevent the proposed method is represented by a mathematical model, the information (the data consumer, time, sensor, an object, duty, and the delegation circumstances, and so on) the privacy attribute of a patient from being exploited illegally patient information from a third party the prevention of the leakage of the privacy information of the patient in synchronization with the attribute information between the parties.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.76-90
• /
• 2024

Although artificial intelligence (AI) can be utilized in various domains such as smart city, healthcare, it is limited due to concerns about the exposure of personal and sensitive information. In response, the concept of distributed machine learning has emerged, wherein learning occurs locally before training a global model, mitigating the concentration of data on a central server. However, overall learning phase in a collaborative way among multiple participants poses threats to data privacy. In this paper, we systematically analyzes recent trends in privacy protection within the realm of distributed machine learning, considering factors such as the presence of a central server, distribution environment of the training datasets, and performance variations among participants. In particular, we focus on key distributed machine learning techniques, including horizontal federated learning, vertical federated learning, and swarm learning. We examine privacy protection mechanisms within these techniques and explores potential directions for future research.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.3
• /
• pp.691-701
• /
• 2015

Recently, with the growing number of services using personal information, government offices' tasks have become more dependent to personal information. Various policies and systems have been made and managed for the safe use of personal information in the circumstances that inevitably require the use of personal information, but the personal information privacy incidents and their scale are on a constant increase. Thus, Korea has been implementing personal information protection management system since 2008 to examine whether public organizations observe the personal information protection act and to how well they manage the personal information, and to improve what is insufficient in the process. However, despite high scores of the outcomes of the system, questions about the effectiveness of the outcomes and about the actual manage level are being raised. Thus, this study seeks to analyze public organizations' activities to protect personal information and the effectiveness of their foundation efforts for them by using the DEA model, and to propose a new model to enhance the effectiveness of the outcomes of personal information protection management system by reflecting them into the outcomes of system, using the derived effectiveness.