• The Journal of the Korea Contents Association
• /
• v.17 no.3
• /
• pp.231-237
• /
• 2017

Threat intelligences collected from cyber incident sharing system and security events collected from Security Information & Event Management system are analyzed and coped with expanding malicious code rapidly with the advent of big data. Analytical classification of the threat intelligence in cyber incidents requires various features of cyber observable. Therefore it is necessary to improve classification accuracy of the similarity by using multi-profile which is classified as the same features of cyber observables. We propose a multi-profile ensemble model performed similarity analysis on cyber incident of threat intelligence based on both attack types and cyber observables that can enhance the accuracy of the classification. We see a potential improvement of the cyber incident analysis system, which enhance the accuracy of the classification. Implementation of our suggested technique in a computer network offers the ability to classify and detect similar cyber incident of those not detected by other mechanisms.

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.197-208
• /
• 2020

Based on the network infrastructure advanced in the information knowledge society, the structure of computer net work is operated by establishing the composition of network in various forms that have secured the security. In case of computer network of national/public organizations, it is necessary to establish the technical and managerial securit y environment even considering the characteristics of each organization and connected organizations. For this, the im portance of basic researches for cyber training by analyzing the technical/managerial vulnerability and cyber threats based on the classification and map of cyber threats according to the characteristics of each organization is rising. T hus, this study aims to analyze each type of external/internal cyber threats to computer network of national/public o rganizations established based on the dualistic infrastructure network of internet and national information network, a nd also to present the cyber threat framework for drawing the elements of cyber security training, by drawing and analyzing the actual elements of cyber threats through the case-based scenario.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.587-596
• /
• 2024

Cyber Attack and Cyber Threat are getting confused and evolved. Therefore, using AI(Artificial Intelligence), which is the most important technology in Fourth Industry Revolution, to build a Cyber Threat Detection System is getting important. Especially, Government's SOC(Security Operation Center) is highly interested in using AI to build SOAR(Security Orchestration, Automation and Response) Solution to predict and build CTI(Cyber Threat Intelligence). In this thesis, We introduce the Cyber Threat Detection System by analyzing Network Traffic and Web Application Firewall(WAF) Log data. Additionally, we apply the well-known TF-IDF(Term Frequency-Inverse Document Frequency) method and AutoML technology to classify Web traffic attack type.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1245-1252
• /
• 2022

As regulatory bodies require full implementation of security controls in nuclear power plants (NPPs), security functions for critical digital assets are currently being developed. For the ultimate introduction of security controls, not alternative measures, it is important to understand the relationship between possible cyber threats to NPPs and security controls to prevent them. To address the effectiveness of the security control implementation, this study investigated the types of cyber threats that can be prevented when the security controls are implemented through the mapping of the reorganized security controls in RS-015 to cyber threats on NPPs. Through this work, the cyber threat that each security control can prevent was confirmed, and the effectiveness of several strategies for implementing the security controls were compared. This study will be a useful reference for utilities or researchers who cannot use design basis threat (DBT) directly and be helpful when introducing security controls to NPPs that do not have actual security functions.

• Convergence Security Journal
• /
• v.20 no.5
• /
• pp.75-80
• /
• 2020

Damage caused by ransomware has continued to increase since last year, but cyber operations are managed without any separate classification of ransomware types in the military's guidelines for carrying out cyber operations. However, unlike other malware, ransomware is a threat that could paralyze all defense operations in one moment, and the military should reevaluate ransomware and take countermeasures. Accordingly, this paper aims to analyze the assets, vulnerabilities, and threats related to defense information service based on information security risk management, and propose alternatives to ensure continuity of defense work from ransomware threats.

• The Journal of the Korea Contents Association
• /
• v.16 no.11
• /
• pp.139-153
• /
• 2016

Cyber incident collected from cyber-threat-intelligence sharing Center is growing rapidly due to expanding malicious code. It is difficult for Incident analysts to extract and classify similar features due to Cyber Attacks. To solve these problems the existing Similarity Analysis Method is based on single or multiple cyber observable of similar incidents from Cyber Attacks data mining. This method reduce the workload for the analysis but still has a problem with enhancing the unreality caused by the provision of improper and ambiguous information. We propose a incident analysis model performed similarity analysis on the hierarchically classified cyber observable based on cyber incident that can enhance both availability by the provision of proper information. Appling specific cyber incident analysis model, we will develop a system which will actually perform and verify our suggested model.

• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.99-104
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.2
• /
• pp.329-337
• /
• 2013

Cyber threats of the ICS(Industrial Control System) has been researched on the level to the threat to the network service as well as a specific system, even if the extent of damage was not intended. Although some range of "security" just include the protection of systems against the deliberate attacks of terrorists or cyber hackers, often more damage is done by carelessness, and equipment failures than by those deliberate attacks. This paper presented a taxonomy for classifying all abnormal behaviors of ICS, including deliberate attacks, inadvertent mistakes, equipment failures, and software problems. The classification criteria of ICS abnormal behaviors was selected to highlight commonalities and important features of deliberate attacks as well as inadvertent actions.

• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.165-171
• /
• 2018

The most threatening attack that has become a hot topic of recent IT security is APT Attack.. So far, there is no way to respond to APT attacks except by using artificial intelligence techniques. Here, we have implemented a machine learning algorithm for analyzing cyber threat data using machine learning method, using a data set that collects cyber attack cases using Scikit Learn, a big data machine learning framework. The result showed an attack classification accuracy close to 70%. This result can be developed into the algorithm of the security control system in the future.