• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.26 no.3
• /
• pp.272-277
• /
• 2017

CCTV image processing techniques have been developed for safety management in manufacturing sites. However, CCTV growth has become a social problem for video surveillance with regard to privacy. This study aims to manage the safety system efficiently and protect privacy simultaneously. In this study, the CCTV monitoring system is composed of five steps (accident monitoring, detection, notification, management, restoration). De-identified image is observed when we are in a normal situation. De-identified image changes to identified image when it detects an accident. As soon as it detects an accident, the accident information is sent to the safety administrator. Then the administrator could conduct safety measures. Afterward, accumulated accident data could be used for statistical data that could be utilized as analyzing expecting accident.

• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.245-257
• /
• 2022

In the Internet of Things (IoT) era, the types of devices used by one user are becoming more diverse and the number of devices is also increasing. However, a forensic investigator is restricted to exploit or collect all the user's devices; there are legal issues (e.g., privacy, jurisdiction) and technical issues (e.g., computing resources, the increase in storage capacity). Therefore, in the digital forensics field, it has been a challenge to acquire information that remains on the devices that could not be collected, by analyzing the seized devices. In this study, we focus on the fact that multiple devices share data through account synchronization of the online platform. We propose a novel way of identifying the user's interest through analyzing the remnants of targeted advertising which is provided based on the visited websites or search terms of logged-in users. We introduce a detailed methodology to pick out the targeted advertising from cache data and infer the user's interest using deep learning. In this process, an improved learning model considering the unique characteristics of advertisement is implemented. The experimental result demonstrates that the proposed method can effectively identify the user interest even though only one device is examined.

• Current Optics and Photonics
• /
• v.6 no.5
• /
• pp.453-462
• /
• 2022

Blockchain technology provides a decentralized and peer-to-peer network, which has the advantages of transparency and immutability. In this paper, a novel secure authentication scheme applying digital holography to blockchain technology is proposed to protect privacy information in network nodes. The transactional information of the node is chained permanently and immutably in the blockchain to ensure network security. By designing a novel two-dimensional (2D) array data structure of the block, a proof of work (PoW) in the blockchain is executed through digital holography technology to verify true authentication and legal block linkage. A hash generated from the proposed algorithm reveals a random number of 2D array data. The real identity of each node in the network cannot be forged by a hacker's tampering because the privacy information of the node is encrypted using digital holography and stored in the blockchain. The reliability and feasibility of the proposed scheme are analyzed with the help of the research results, which evaluate the effectiveness of the proposed method. Forgery by a malicious node is impossible with the proposed method by rejecting a tampered transaction. The principal application is a secure anonymity system guaranteeing privacy information protection for handling of large information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2589-2604
• /
• 2024

Brain tumors, characterized by uncontrollable cellular growths, are a significant global health challenge. Navigating the complexities of tumor identification due to their varied dimensions and positions, our research introduces enhanced methods for precise detection. Utilizing advanced learning techniques, we've improved early identification by preprocessing clinical dataset-derived images, augmenting them via a Generative Adversarial Network, and applying an Improved Privacy-Preserving Collaborative Convolutional Neural Network (IPC-CNN) for segmentation. Recognizing the critical importance of data security in today's digital era, our framework emphasizes the preservation of patient privacy. We evaluated the performance of our proposed model on the Figshare and BRATS 2018 datasets. By facilitating a collaborative model training environment across multiple healthcare institutions, we harness the power of distributed computing to securely aggregate model updates, ensuring individual data protection while leveraging collective expertise. Our IPC-CNN model achieved an accuracy of 99.40%, marking a notable advancement in brain tumor classification and offering invaluable insights for both the medical imaging and machine learning communities.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.1
• /
• pp.79-86
• /
• 2002

Recently, it is shown that the unrelated quest ion randomized response models proposed by Moors (1971), Folsom et al.(1973), Greenberg et al.(1971) are in capable of protecting the privacy of the respondent. Thus, in this paper, we review recent days research tendency. Also modification model of Mahmood et al.(1998) is proposed, and we show th at this model is more efficient than Greenberg et al.(1969). Furthermore we treat the privacy protection based on Lanke's (1975) risk of suspicion measure.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.5
• /
• pp.1115-1133
• /
• 2024

With the rapid development of AI technology, AI systems are increasingly collecting, processing, and utilizing personal information in large quantities. As a result, transparency and accountability of personal information processing by AI systems, ensuring the rights of information subjects, and minimizing the risk of personal information infringement are becoming important issues. However, the existing privacy policy only discloses the personal information processing in general, and there is no privacy policy for AI systems. In order to solve these problems, In response to the implementation of the privacy policy evaluation system in accordance with the revision of the Personal Information Protection Act, we propose a new AI system privacy policy establishment and disclosure for personal in the design, development and operation of AI system. This study is expected to play a complementary role to the regulations on the right of data subjects to request an explanation and exercise the right of refusal for automated decisions under the current Personal Information Protection Act.

• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.223-235
• /
• 2011

Performing approximate data matching has always been an intriguing problem for both industry and academia. This task becomes even more challenging when the requirement of data privacy rises. In this paper, we propose a novel technique to address the problem of efficient privacy-preserving approximate record linkage. The secure framework we propose consists of two basic components. First, we utilize a secure blocking component based on phonetic algorithms statistically enhanced to improve security. Second, we use a secure matching component where actual approximate matching is performed using a novel private approach of the Levenshtein Distance algorithm. Our goal is to combine the speed of private blocking with the increased accuracy of approximate secure matching.

• Journal of Preventive Medicine and Public Health
• /
• v.40 no.2
• /
• pp.122-129
• /
• 2007

During the last decade, genomic cohort study has been developed in many countries by linking health data and genetic data in stored samples. Genomic cohort study is expected to find key genetic components that contribute to common diseases, thereby promising great advance in genome medicine. While many countries endeavor to build biobank systems, biobank-based genome research has raised important ethical concerns including genetic privacy, confidentiality, discrimination, and informed consent. Informed consent for biobank poses an important question: whether true informed consent is possible in population-based genomic cohort research where the nature of future studies is unforeseeable when consent is obtained. Due to the sensitive character of genetic information, protecting privacy and keeping confidentiality become important topics. To minimize ethical problems and achieve scientific goals to its maximum degree, each country strives to build population-based genomic cohort research project, by organizing public consultation, trying public and expert consensus in research, and providing safeguards to protect privacy and confidentiality.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.571-585
• /
• 2021

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

• Journal of Convergence for Information Technology
• /
• v.8 no.5
• /
• pp.107-113
• /
• 2018

With the rapid development of big data and Internet technologies among IT technologies, it is being changed into an environment where data stored in the cloud environment can be used wherever the Internet is connected, without storing important data in an external storage device such as USB. However, protection of users' privacy information is becoming increasingly important as the data being processed in the cloud environment is changed into an environment that can be easily handled. In this paper, we propose a user-reserving management model that can improve the user 's service quality without exposing the information used in the cloud environment to a third party. In the proposed model, user group is grouped into virtual environment so that third party can not handle user's privacy information among data processed in various cloud environments, and then identity property and access control policy are processed by block chain.