• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.19-22
• /
• 2009

This thesis offers forecast & warning algorithm about the accessing networks though statistical sampling methods to prevent computer terrors. These networks are occurred among U-city network groups. The main characteristic of current computer attacks is avoiding well-known detection patterns by successive changes in spreading speeds and attacking codes. The improvement of attacking stills leads to a problem causing the defense-time delay and creates vicious cycle that tries to fix networks after damage. Proposed algorithm notices and warns the potential attacking areas through defecting previous attacking signs, analysing attaching results ed tracing attaching sources at the beginning of the attack.

• Journal of Korea Multimedia Society
• /
• v.20 no.4
• /
• pp.629-639
• /
• 2017

Interpolation based information hiding methods are widely used to get information security. Conventional interpolation methods use the neighboring pixel value and simple calculation like average to embed secret bit stream into the image. But these information hiding methods are not appropriate to color images like military images because the characteristics of military images are not considered and these methods are restricted in grayscale images. In this paper, the new information hiding method based on interpolation using RGB pixel values of color image is proposed and the effectiveness is analyzed through experiments.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.314-317
• /
• 2017

최근 ICT 기술이 발달함에 따라 전쟁의 양상이 물리적에서 사이버전으로 이동되고 있으며 이미 사이버 공간을 제 5의 전장으로 불리운다. 또한 오랜 기간 동안 단계적으로 준비 과정을 거쳐 공격하는 APT 사례가 증가함에 따라 공격 징후를 사전에 탐지해 선제 대응하는 사이버 킬 체인이라는 방안이 각광받고 있다. 이러한 사이버 킬 체인 중 가장 기초가 되는 감시/정찰을 수행하기 위한 방안을 연구하면서 적의 영역에 침투했다는 가정하에서 정보를 수집하는 프로그램을 설계 및 제작해 보았다.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.861-864
• /
• 2017

사이버 ISR을 통하여 정보를 획득하는 과정에서 데이터를 추출하고 이를 스스로 가공하여 의사결정에 도움을 줄 수 있는 에이전트를 연구하는 과정에서 폐쇄망에 침투했을 경우 이를 효과적으로 감시 정찰할 수 있는 방법을 논의한다. 폐쇄망으로 인하여 침투한 컴퓨터에 심어진 에이전트는 C&C서버와 원활한 교류가 불가능하게 되는데, 이때 스스로 살아남아 지속적으로 데이터를 수집하며, 분석을 하기 위해서는 한정된 자원과 시간을 활용하여야 발각되지 않고 계속하여 임무를 수행할 수 있다. 특히 분석하는 과정에서 많은 자원과 시간을 활용하는 때 이를 해결하기 위해 본인은 점진적 학습방법을 이용하는 것을 제안하며, 일괄학습 방법과 함께 비교하는 실험을 해보았다.

• Electronics and Telecommunications Trends
• /
• v.32 no.6
• /
• pp.73-82
• /
• 2017

Moving Target Defense(MTD) is a novel security technology concept in which the IT infrastructure changes its form actively and prevents various types of cyber attacks. Network address moving technology is the field that has been most actively researched in terms of MTD. A number of studies on network address moving published over the last decade have suggested a virtual address-based network address moving technology for efficiency in the implementation. However, virtual address-based network address moving technology has serious vulnerabilities in terms of security and availability. This paper examines the technological characteristics of the existing studies and analyzes their limitations. It suggests security requirements to be considered when designing the network address moving technology through a technological analysis.

• Journal of Korea Multimedia Society
• /
• v.19 no.9
• /
• pp.1669-1678
• /
• 2016

There are many kinds of military images used in naval combat system because various sensors are operated. The military images are displayed, analysed and stored with analysed informations according to the tactical purpose on combat system. These images are used to target detection, analysis and classification. Thus the analysed information and images must be secured, the information hiding methods are the most eligible solutions to get secured informations and images. In this paper, the hybrid information hiding method based on the characteristics of the military images is proposed and the effectiveness is shown by experiments.

• Journal of Information Processing Systems
• /
• v.15 no.1
• /
• pp.100-115
• /
• 2019

Malicious code distribution on the Internet is one of the most critical Internet-based threats and distribution technology has evolved to bypass detection systems. As a new defense against the detection bypass technology of malicious attackers, this study proposes the automated tracing of malicious websites in a malware distribution network (MDN). The proposed technology extracts automated links and classifies websites into malicious and normal websites based on link structure. Even if attackers use a new distribution technology, website classification is possible as long as the connections are established through automated links. The use of a real web-browser and proxy server enables an adequate response to attackers' perception of analysis environments and evasion technology and prevents analysis environments from being infected by malicious code. The validity and accuracy of the proposed method for classification are verified using 20,000 links, 10,000 each from normal and malicious websites.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.42-49
• /
• 2021

As cyber attacks become more intelligent, there is difficulty in detecting advanced attacks in various fields such as industry, defense, and medical care. IPS (Intrusion Prevention System), etc., but the need for centralized integrated management of each security system is increasing. In this paper, we collect big data for intrusion detection and build an intrusion detection platform using deep learning and CNN (Convolutional Neural Networks). In this paper, we design an intelligent big data platform that collects data by observing and analyzing user visit logs and linking with big data. We want to collect big data for intrusion detection and build an intrusion detection platform based on CNN model. In this study, we evaluated the performance of the Intrusion Detection System (IDS) using the KDD99 dataset developed by DARPA in 1998, and the actual attack categories were tested with KDD99's DoS, U2R, and R2L using four probing methods.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.1
• /
• pp.39-43
• /
• 2023

In ground weapon systems, the design and analysis technology for water operation stability is a relatively unknown area compared to maritime weapon systems. Through this study, it was confirmed that our weapon system satisfies the criteria for stability on the water when considering the operational concept and operational performance. However, there is a limitation of the study that it did not perform verification tests on the actual system. Therefore, in the future research and weapon system acquisition process, a procedure to prove the stability through freeboard analysis using the actual system is required.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.510-516
• /
• 2023

세계화가 진행됨에 따라 다양한 문화의 음악을 즐기는 사람들이 늘어나고, 해외 팬들이 외국 노래를 이해하고 따라 부를 수 있는 접근성을 확보하는 것이 중요해졌다. 이를 위해 본 논문에서는 노래 가사 데이터에 특화된 영어-한국어 번역 모델 리리코(LyriKOR)를 제시한다. 리리코는 영어 노래를 한국어로 번역하여 그 의미를 담아낼 뿐만 아니라, 번역 결과물이 원곡의 선율과 리듬에 어느 정도 부합하도록 하여 한국어로 바로 따라 부를 수 있도록 하는 것을 목표로 한다. 이를 위해 번역과 음절 조정의 두 단계(two-stage)를 거쳐 제한된 데이터로 음절 정렬된 번역 모델을 훈련하는 새로운 방법을 소개한다. 모델 코드는 여기에서 볼 수 있다.