• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.201-211
• /
• 2022

According to the recent change in the cybersecurity paradigm, research on anomaly detection methods using machine learning and deep learning techniques, which are AI implementation technologies, is increasing. In this study, a comparative study on data preprocessing techniques that can improve the anomaly detection performance of a GRU (Gated Recurrent Unit) neural network-based intrusion detection model using NGIDS-DS (Next Generation IDS Dataset), an open dataset, was conducted. In addition, in order to solve the class imbalance problem according to the ratio of normal data and attack data, the detection performance according to the oversampling ratio was compared and analyzed using the oversampling technique applied with DCGAN (Deep Convolutional Generative Adversarial Networks). As a result of the experiment, the method preprocessed using the Doc2Vec algorithm for system call feature and process execution path feature showed good performance, and in the case of oversampling performance, when DCGAN was used, improved detection performance was shown.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.4
• /
• pp.61-75
• /
• 2011

Recently, there is significant increasing of massive attacks, which try to infect PCs that visit websites containing pre-implanted malicious code. When visiting the websites, these hidden malicious codes can gain monetary profit or can send various cyber attacks such as BOTNET for DDoS attacks, personal information theft and, etc. Also, this kind of malicious activities is continuously increasing, and their evasion techniques become professional and intellectual. So far, the current signature-based detection to detect websites, which contain malicious codes has a limitation to prevent internet users from being exposed to malicious codes. Since, it is impossible to detect with only blacklist when an attacker changes the string in the malicious codes proactively. In this paper, we propose a novel approach that can detect unknown malicious code, which is not well detected by a signature-based detection. Our method can detect new malicious codes even though the codes' signatures are not in the pattern database of Anti-Virus program. Moreover, our method can overcome various obfuscation techniques such as the frequent change of the included redirection URL in the malicious codes. Finally, we confirm that our proposed system shows better detection performance rather than MC-Finder, which adopts pattern matching, Google's crawling based malware site detection, and McAfee.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.293-295
• /
• 2015

This paper proposed have been the business card information to the computer when creating business card printing agency saved to a file, there is always the risk of personal information leakage. Application file organization information into the card, the name, phone number, email address information, such as is capable of easily accessible because it is not encrypted. This paper proposed it encrypts the information entered on the Business Card application file to automate the process of the card application and simplifying the business card application process minimizes the work of staff and linked directly to the print shop how to automatically delete the print file after the completion of business card printing and research.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.477-486
• /
• 2010

This Study suggests security directions to reconstruct separate network of Smart Grid and information communication network as one communications system and implement Smart Grid integrated information communication network. In addition, it suggests prevention directions to prevent future cyber attacks by reorganizing network as the key three-stage network and separating TCP/IP four layers that consist of existing information communication network from Smart Grid. Moreover, it suggests the foundation for the study and the test by providing current problems of Smart Grid, weak points, and three security models. This study is meaningful to suggest development directions and situations as a technology of future-oriented electric industries, integrate attacks and preventions of TCP/IP Layers with Smart Grid, and seek for a new technology of Smart Grid and future tasks for Smart Grid information security.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.112-118
• /
• 2023

As technology advances, the need for enhanced preparedness against cyber-attacks becomes an increasingly critical problem. Therefore, it is imperative to consider various circumstances and to prepare for cyber-attack strategic technology. This paper proposes a method to solve network security problems by applying reinforcement learning to cyber-security. In general, traditional static cyber-security methods have difficulty effectively responding to modern dynamic attack patterns. To address this, we implement cyber-attack scenarios such as 'Tiny Alpha' and 'Small Alpha' and evaluate the performance of various reinforcement learning methods using Network Attack Simulator, which is a cyber-attack simulation environment based on the gymnasium (formerly Open AI gym) interface. In addition, we experimented with different RL algorithms such as value-based methods (Q-Learning, Deep-Q-Network, and Double Deep-Q-Network) and policy-based methods (Actor-Critic). As a result, we observed that value-based methods with discrete action spaces consistently outperformed policy-based methods with continuous action spaces, demonstrating a performance difference ranging from a minimum of 20.9% to a maximum of 53.2%. This result shows that the scheme not only suggests opportunities for enhancing cybersecurity strategies, but also indicates potential applications in cyber-security education and system validation across a large number of domains such as military, government, and corporate sectors.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.1-7
• /
• 2020

With the increase in cyber attacks, automated IDS using machine learning is being studied. According to recent research, the IDS using the recursive learning model shows high detection performance. However, the simple application of the recursive model may be difficult to reflect the associated session characteristics, as the overlapping session environment may degrade the performance. In this paper, we designed the session management module and applied it to LSTM (Long Short-Term Memory) recursive model. For the experiment, the CSE-CIC-IDS 2018 dataset is used and increased the normal session ratio to reduce the association of mal-session. The results show that the proposed model is able to maintain high detection performance even in the environment where session relevance is difficult to find.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.19-26
• /
• 2014

The advent of smart phones brought adverse effect between devices recently. For example, adverse effects of info-communication with advent of computer. Also, hacking threat aiming cyber space that is getting more advanced is spreading in terms of range and danger, so that it reaches the level that the nation has to concern. In this circumstance, crimes involving info-technology is now problem in society. As internet technology advances, it enlarges the range of hacker's threat to not only smart phones, but ships, aircrafts, buildings, and cars. It could be seen as social threat of between human and human, between machine and machine, and between human and machine. This study discuss these problems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.1
• /
• pp.51-58
• /
• 2020

The use of malware in cyber threats continues to be used in all ages, and will continue to be a major attack method even if IT technology advances. Therefore, researches for detecting such malicious codes are constantly tried in various ways. Recently, with the development of AI-related technology, many researches related to machine learning have been conducted to detect malware. In this paper, we propose a method to detect malware using machine learning. For machine learning detection, we create a feature around each call interval, ie Time Interval, in which API calls occur among dynamic analysis data, and then apply the result to machine learning techniques.

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.125-134
• /
• 2020

The potential security threat is increasing as the supply of ICT products to the defense sector increases with the development of information and communication technology. Attempts to neutralize, such as intelligence gathering and destruction, through attacks on the defense power support system and the intelligence system of the weapons system could pose a fatal threat.Therefore, security measures of supply chain shear system that take into account ICT product production and operation stage to maintenance stage are needed in defense field. In the paper, technical and administrative measures for responding to 12 ICT supply chain security threats at each stage of the defense ICT supply chain life cycle were presented.

• Proceedings of the Korea Information Assurance Society Conference
• /
• 2004.05a
• /
• pp.327-331
• /
• 2004

The new cyber world has created by Internet that is prosperous rapidly. But with the expansion of Internet the hacking and intrusion are also increased very much. Actually there were many incidents in Internet, but the damage was restricted within a local area and local system. However, the Great 1.25 Internet Disturbance has paralyzed the national wide Internet environment. It because the Slammer Worm. The worm is a malformed program that uses both of the hacking and computer virus techniques. It autonomously attacks the vulnerability of Windows system, duplicates and spreads by itself. Jus like the Slammer Worm, almost every worms attack the vulnerability of Windows systems that installed in personal PC. Therefore, the vulnerability in personal PC could destroy the whole Internet world. So, in this paper we propose a Internet Worm Expanding Prevention System that could be installed in personal PC to prevent from expanding the Internet Worm. And we will introduce the results of developed system.