• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.9
• /
• pp.603-614
• /
• 2013

The popularity of mobile devices provides their users with a circumstance that services and information can be accessed wherever and whenever users need. Accordingly, various studies have been proposed personalized methods to improve accessibility of mobile users to information. However, since these personalized methods require users' private information, they gives rise to problems on security. An efficient way to resolve security problems is to estimate user information by using their online and offline behavior. In this paper, for this purpose, it is proposed a novel user information identification system that identifies users' personal and social information by using both his/her behavior on social network services and proximity patterns obtained from GPS data. In the proposed system, personal information of a user like age, gender, and so on is estimated by analyzing SNS texts and POI (Point of Interest) patterns, while social information between a pair of users like family and friend is predicted with proximity patterns between the users. Each identification module is efficiently designed to handle the characteristics of user data like much noise in SNS texts and missing signals in GPS data. In experiments to evaluate the proposed system, our system shows its superiority against ordinary identification methods. This result means that the proposed system can efficiently reflect the characteristics of user data.

• Smart Media Journal
• /
• v.8 no.1
• /
• pp.9-18
• /
• 2019

In the era of the 4th industrial revolution, the big data industry is gathering attention for new business models in the public and private sectors by utilizing various information collected through the internet and mobile. However, although the big data integration and analysis are performed with de-identification techniques, there is still a risk that personal privacy can be exposed. Recently, there are many studies to invent effective methods to maintain the value of data without disclosing personal information. In this paper, a personal information protection system is investigated to boost big data utilization in industrial sectors, such as healthcare and agriculture. The criteria for evaluating the de-identification adequacy of personal information and the protection scope of personal information should be differently applied for each industry. In the field of personal sensitive information-oriented healthcare sector, the minimum value of k-anonymity should be set to 5 or more, which is the average value of other industrial sectors. In agricultural sector, it suggests the inclusion of companion dogs or farmland information as sensitive information. Also, it is desirable to apply the demonstration steps to each region-specific industry.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.185-191
• /
• 2022

개인정보에 대한 경각심 및 중요성 증대에 따라 텍스트 내 개인정보를 탐지하는 태스크가 주목받고 있다. 본 연구에서는 개인정보 탐지 및 비식별화를 위한 개인정보 특화 개체명 태그셋 7개를 고안하는 한편 이를 바탕으로 비식별화된 원천 데이터에 가상의 데이터를 대치하고 개체명을 주석함으로써 개인정보 특화 개체명 데이터셋을 구축하였다. 개인정보 분류 실험에는 KR-ELECTRA를 사용하였으며, 실험 결과 일반 개체명 및 정규식 바탕의 규칙 기반 개인정보 탐지 성능과 비교하여 특화 개체명을 활용한 딥러닝 기반의 개인정보 탐지가 더 높은 성능을 보임을 확인하였다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.6
• /
• pp.1593-1603
• /
• 2016

In the smart grid environment, there are various security threats. In particular, exposure of smart meter data can lead to serious privacy violation. In this paper, we propose a method for de-identification method of metering data. The proposed method is to de-identify the time data and the numeric data, respectively. Therefore, it can't analyze the pattern information from the metering data. In addition, there is an advantage that the query is available, such as the range of search in the database for statistical analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.339-342
• /
• 2016

스마트그리드는 기존 전력망의 비효율적인 운영, 이산화탄소 과다 배출, 전력피크의 문제를 해결하기 위한 방법으로 주목받고 있다. 하지만, 기존의 ICT가 도입되고 구조가 복잡해짐에 따라 개인정보를 침해 할 수 있는 가능성이 증가하게 되었다. 본 논문에서는 스마트그리드 내에서 개인정보를 다루는 기기, 시스템, 데이터와 같은 자산을 식별하여 공격자 입장에서의 공격 목표를 설정한 뒤, Attack Tree 방법을 통하여 세부적인 위협을 식별하였다. 분석 결과, 스마트그리드 환경은 기존의 ICT 기술이 접목되기 때문에 스마트그리드 구조상 발생할 수 있는 위협뿐 만 아니라 기존의 기술들에서 발생할 수 있는 위협도 함께 존재했다.

• Informatization Policy
• /
• v.23 no.4
• /
• pp.38-58
• /
• 2016

The ever-evolving Internet environment along with changes in the mass media has been creating a new way of communicating in the virtual cyber world. The Internet users have more services at their disposal to communicate with ease. Such a new way of communication styles, however, makes them vulnerable to personal information leakage, increasing the concerns of cyber security. A thorny issue is how we can control the disclosure of personal information. Lately, the Korean government implemented privacy policies to resolve and prevent personal information leakage incidents that incur social problems. Here, we seek to identify problems in the privacy policies for better solutions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.206-208
• /
• 2022

As the big data industry has recently developed significantly, interest in privacy violations caused by personal information leakage has increased. There have been attempts to automate this through named entity recognition in natural language processing. In this paper, named entity recognition data is constructed semi-automatically by identifying sentences with de-identification information from de-identification information in Korean Wikipedia. This can reduce the cost of learning about information that is not subject to de-identification compared to using general named entity recognition data. In addition, it has the advantage of minimizing additional systems based on rules and statistics to classify de-identification information in the output. The named entity recognition data proposed in this paper is classified into twelve categories. There are included de-identification information, such as medical records and family relationships. In the experiment using the generated dataset, KoELECTRA showed performance of 0.87796 and RoBERTa of 0.88.

• Review of KIISC
• /
• v.1 no.1
• /
• pp.124-129
• /
• 1991

정보 보안의 요소는 인가되지 않은 사람이 시스템에 액세스(Access)하거나 인가없 이 사용하는 것을 방지하는 액세스 통제이다. 이를 위해서 정보의 기밀정도에 따라 보호정 도를 결정하는 기밀등급분류가 이루어져 정보를 선택관리하는체계가 이루어 져야한다. 정 보를 선택관리하기 위해서는 보호할 만한 정보를 식별하고, 식별된 중요정보를 어떤 방법 으로 유지, 관리, 이용할 것인지를 규정하는 것이 필요하다. 본 논문에서는 정보 기밀등급 의 체계적인 분류방법에 대해 살펴보기로 한다.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.455-464
• /
• 2009

To overcome article-oriented search functions and provide author-oriented ones, a namesake problem for author names should be solved. Author disambiguation, proposed as its solution, assigns identifiers of real individuals to author name entities. Although recent state-of-the-art approaches to author disambiguation have reported above 90% performance, there are few academic information services which adopt author-resolving functions. This paper describes a large-scale test set for author disambiguation which was created by KISTI to foster author resolution researches. The result of these researches can be applied to academic information systems and make better service. The test set was constructed from DBLP data through web searches and manual inspection, Currently it consists of 881 author names, 41,673 author name entities, and 6,921 person identifiers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.1010-1011
• /
• 2013

본 논문에서는 국방과학연구소에서 운용하는 KOMSAR(Korea Miniature Synthetic Aperture Radar)장비로 측정한 실제 항공기의 데이터를 이용하여 효율적인 표적식별을 수행하였다. 표적식별과정은 수신된 모든 데이터에 대하여 거리측면도를 구한 다음 4개의 표적으로 분리한 후, 효과적인 특성벡터를 구성하여 nearest neighbor(NN) 구분기로 표적식별 성능을 수행하였다. 표적식별수행 결과, 높은 구분성능으로 구분이 가능하였다.