• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.660-663
• /
• 2018

최근 5년간 식용 나물과 독초를 구별하지 못한 채 섭취하여 다수의 환자가 발생하였다. 본 논문에서는 인체에 치명적인 결과를 일으킬 수 있는 독초를 CNN을 통해 분류하는 시스템을 제안한다. 부족한 양의 샘플 데이터는 데이터 확장 기법을 통해 확보하였고, 연구에 사용된 하드웨어의 한계를 극복하기 위해 전이학습을 적용하였다. 실험은 데이터 확장과 전이 학습 적용 여부에 따라 4가지 유형별로 진행되었으며, 각 유형은 20회씩 반복한 테스트의 결과를 종합하여 평균을 내었다. 이와 같은 실험에서 의미 있는 결과를 얻었다. 본 논문의 시스템을 이용한 독초 섭취 사고의 예방이 기대된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1137-1142
• /
• 2017

Cyber hacking attacks and cyber terrorism are damaging to the lives of the people, and in the end, national security is threatened. Cyber-hacking attacks leaked nuclear power cooling system design drawings, cyber accidents such as hacking of Cheongwadae's homepage and hacking of KBS stations occurred. The Act on Information and Communication Infrastructure Protection, Promotion of Information and Communication Network Utilization and Information Protection, and the Personal Information Protection Act remove the responsibility for cyber attacks, but it is difficult to prevent attacks by hackers armed with new technologies. This paper studies the development of cyber security experts for cyber security. Build a Knowledge Data Base for cyber security professionals. Web hacking, System hacking, and Network hacking technologies and evaluation. Through researches on the operation and acquisition of cyber security expert certification, we hope to help nurture cyber security experts for national cyber security.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.727-730
• /
• 2017

복잡한 알고리즘과 고가의 센서 없이도 동적 환경에서 목표를 탐색하는 이동 로봇 시스템을 제안하였다. 탐색환경의 지도를 제작하지 않고 단순한 목표를 가진 하부 모듈의 결합만을 사용하는 포섭구조를 활용하였다. 제안한 시스템의 유용성 검증을 위해 실험을 하였고, 그 결과 목표를 찾아 감을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1534-1536
• /
• 2015

동영상에서 학습을 통한 특정인의 탐지는 한 개의 프레임 당 많은 시간이 소모된다. 따라서 특정인의 위치를 파악하면서도 탐색할 프레임의 수를 줄이는 것이 필요하다. 우리는 관찰되는 장소의 특징을 이용하여 일정 범위를 생략하는 탐색 기법을 제안하고 성능을 측정하였다. 실험결과 제안한 방법에서 어느 정도 유의미한 결과를 얻을 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.796-799
• /
• 2020

신경망은 주로 전체 데이터를 중앙에서 학습시키거나 상황에 따라 데이터나 모델을 나누어 분산학습 방법으로 처리해 왔다. 그러나 데이터의 양의 증가와 보안적 이유로 인해 모든 환경에서 기존의 방법을 쓰기에 어려움이 있다. 본 연구에서는 제한된 데이터만으로 모든 데이터로 학습한 것과 같은 학습 효과를 내기 위한 방법을 제안한다. 데이터의 구성이 다른 두 가지 환경인 V-환경과 H-환경에서 학습한 모델을 어떤 방법으로 통합해야 기존의 성능과 비슷한 성능을 낼 수 있는지 연구한다. 우리는 가중치를 합치는 방법을 avg, max, absmas 3가지 방법으로 실험하였으며, 실험 결과로 V-환경에서는 기존의 성능과 비슷한 성능을 보였으며, H-환경에서는 기존의 성능에는 부족하지만, 의미 있는 성능을 보였다.

• Journal of Information Technology Services
• /
• v.15 no.1
• /
• pp.67-79
• /
• 2016

This study aims to present the necessary elements that should be part of South Korea's National Defense Strategy against the recent North Korean cyber-attacks. The elements proposed in this study also reflect the recent trend of cyber-attack incidents that are happening in the Unites States and other countries and have been classified into the three levels of cyber incidents: cyberwarfare, cyberterrorism and cybercrime. As such, the elements proposed are presented in accordance with this classification system. In order to properly take into account the recent trend of cyber-attacks perpetrated by North Korea, this paper analyzed the characteristics of recent North Korean cyber-attacks as well as the countermeasures and responses of South Korea. Moreover, by making use of case studies of cyber-attack incidents by foreign nations that threaten national security, the response measures at a national level can be deduced and applied as in this study. Thus, the authors of this study hope that the newly proposed elements here within will help to strengthen the level of Korea's cyber security against foreign attacks, specifically that of North Korea such as the KHNP hacking incidents and so on. It is hoped that further damage such as leakage of confidential information, invasion of privacy and physical intimidation can be mitigated.

• Convergence Security Journal
• /
• v.22 no.1
• /
• pp.19-27
• /
• 2022

With the innovative development of ICT technology, hacking techniques of hackers are also evolving into sophisticated and intelligent hacking techniques. Threat detection research to counter these cyber threats was mainly conducted in a passive way through hacking damage investigation and analysis, but recently, the importance of cyber threat information collection and analysis is increasing. A bot-type automation program is a rather active method of extracting malicious code by visiting a website to collect threat information or detect threats. However, this method also has a limitation in that it cannot prevent hacking damage because it is a method to identify hacking damage because malicious code has already been distributed or after being hacked. Therefore, to overcome these limitations, we propose a model that detects actual threats by acquiring and analyzing threat information while identifying and managing cyber bases. This model is an active and proactive method of collecting threat information or detecting threats outside the boundary such as a firewall. We designed a model for detecting threats using cyber strongholds and validated them in the defense environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.1
• /
• pp.215-223
• /
• 2019

The recent trend of cyber attack threat is mainly APT (Advanced Persistent Threat) attack. This attack is a combination of hacking techniques to try to steal important information assets of a corporation or individual, and social engineering hacking techniques aimed at human psychological factors. Spear phishing attacks, one of the most commonly used APT hacking techniques, are known to be easy to use and powerful hacking techniques, with more than 90% of the attacks being a key component of APT hacking attacks. The existing research for cyber security threat defense is mainly focused on the technical and policy aspects. However, in order to preemptively respond to intelligent hacking attacks, it is necessary to study different aspects from the viewpoint of social engineering. In this study, we analyze the correlation between human personality type (DISC) and cyber security threats, focusing on spear phishing attacks, and present countermeasures against security threats from a new perspective breaking existing frameworks.

• Convergence Security Journal
• /
• v.19 no.1
• /
• pp.19-30
• /
• 2019

As the 4th industrial revolution has recently become a hot topic, the importance of autonomous vehicles has increased and interest has been increasing worldwide, and accidents involving autonomous vehicles have also occurred. With the development of autonomous vehicles, the possibility of a cyber-hacking threat to the car network is increasing. Various countries, including the US, UK and Germany, have developed guidelines to counter cyber-hacking of autonomous vehicles, In the case of Korea, limited temporary operation of autonomous vehicles is being carried out, but the legal system to be applied in case of accidents caused by vehicle network hacking is insufficient. In this paper, based on the existing legal system, we examine the civil liability caused by the cyber hacking of the autonomous driving car, while we propose a law amendment suited to the characteristics of autonomous driving car and a legal system improvement plan that can give sustainable trust to autonomous driving car.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.8
• /
• pp.1052-1057
• /
• 2020

With the development of new ICT technology, smart keys for vehicles are terminals with ICT technology. Therefore, when the vehicle and the smart key communicate with RF, a cyber hacking attack is possible. Cyber-attacks on smart keys can pose a threat to vehicle theft and vehicle control. Therefore, it is necessary to study hacking attacks and vulnerabilities of smart keys for autonomous vehicles. In this paper, we analyze the cyber attack case of RF communication for vehicles and smart keys. In addition, a real RF cyber attack on the smart key is performed, and the vulnerability of radio wave replication in the same frequency band is found. In this paper, we analyze the vulnerability of RF communication between vehicles and smart keys, and propose a countermeasure against cyber security. In the future, plans to strengthen cyber attacks and security through the popularization of autonomous vehicles will become basic data to protect human and vehicle safety.