• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.847-857
• /
• 2018

As the number of malicious code increases steeply, cyber attack victims targeting corporations, public institutions, financial institutions, hospitals are also increasing. Accordingly, academia and security industry are conducting various researches on malicious code detection. In recent years, there have been a lot of researches using machine learning techniques including deep learning. In the case of research using Convolutional Neural Network, ResNet, etc. for classification of malicious code, it can be confirmed that the performance improvement is higher than the existing classification method. However, one of the characteristics of the target attack is that it is custom malicious code that makes it operate only for a specific company, so it is not a form spreading widely to a large number of users. Since there are not many malicious codes of this kind, it is difficult to apply the previously studied machine learning or deep learning techniques. In this paper, we propose a method to classify malicious codes when the amount of samples is insufficient such as targeting type malicious code. As a result of the study, we confirmed that the accuracy of 97% can be achieved even with a small amount of data by applying the Memory Augmented Neural Networks model.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.1151-1153
• /
• 2007

P2P 및 Mobile Network, Reputations System 등의 분산 시스템은 sybil attack 에 노출되어 있다. sybil attack 은 한 명의 사용자가 다수의 식별자를 가진 것으로 위장하여 시스템 내에서 마치 실제 다수의 사용자인 양 시스템을 악용하는 공격방법이다. sybil attack 을 막기 위한 다양한 노력이 진행되었고, 최근에 SybilGuard 라는 social network 를 이용한 방어 방법이 제시되었다. SybilGuard 는 악의적인 사용자를 막기 위하여, Random Walk 의 변형이면서 결정적인 경로의 특징을 가지는 임의경로(Random Route)를 사용하여 악의적인 사용자의 sybil attack 을 방어한다. SybilGuard 는 sybil node 의 개수를 제한하고, 이들을 하나의 동일한 그룹으로 분류할 수 있도록 하여 시스템 내에서 가짜 식별자의 개수를 제한한다. 이를 위해 각 노드가 시스템에 돌어올 때 Verifier(V)노드가 이들 노드를 확인하게 되는데, 이를 위해 시스템 내의 선한 노드(Honest Node)를 사용하여 이들을 확인한다. 이 때, honest node 들은 verifier 의 요청에 따라 확인요청을 수행하게 되는데, social network 의 특성상 몇몇 노드들은 사회적인 명망으로 매우 큰 링크수를 가지게 될 것이며, 따라서 이들 노드들이 처리해야할 요청의 양이 매우 많아지게 될 것이다. 따라서 이들 honest node 들 간에 로드분포를 균등하게 하는 것이 요구되며, 이 논문에서는 부하 조절을 하기 위한 기법을 제시하고, 이들을 평가한다.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.27-37
• /
• 2022

Virtual private network (VPN) services are used in various environments related to national security, such as defense companies and defense-related institutions where digital communication environment technologies are diversified and access to network use is increasing. However, the number of cyber attacks that target vulnerable points of the VPN has annually increased through technological advancement. Thus, this study identified security requirements by performing STRIDE threat modeling to prevent potential and new vulnerable points that can occur in the VPN. STRIDE threat modeling classifies threats into six categories to systematically identify threats. To apply the proposed security requirements, this study analyzed functions of the VPN and formed a data flow diagram in the VPN service process. Then, it collected threats that can take place in the VPN and analyzed the STRIDE threat model based on data of the collected threats. The data flow diagram in the VPN service process, which was established by this study, included 96 STRIDE threats. This study formed a threat scenario to analyze attack routes of the classified threats and derived 30 security requirements for each element of the VPN based on the formed scenario. This study has significance in that it presented a security guideline for enhancing security stability of the VPN used in facilities that require high-level security, such as the Ministry of National Defense (MND).