• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.65-72
• /
• 2023

This paper proposes a method for detecting malicious domains considering human habitual characteristics by building a Deep Learning model based on LSTM (Long Short-Term Memory). DGA (Domain Generation Algorithm) malicious domains exploit human habitual errors, resulting in severe security threats. The objective is to swiftly and accurately respond to changes in malicious domains and their evasion techniques through typosquatting to minimize security threats. The LSTM-based Deep Learning model automatically analyzes and categorizes generated domains as malicious or benign based on malware-specific features. As a result of evaluating the model's performance based on ROC curve and AUC accuracy, it demonstrated 99.21% superior detection accuracy. Not only can this model detect malicious domains in real-time, but it also holds potential applications across various cyber security domains. This paper proposes and explores a novel approach aimed at safeguarding users and fostering a secure cyber environment against cyber attacks.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.9-19
• /
• 2023

Smart cars, which incorporate information and communication technologies (ICT) to improve driving safety and convenience for drivers, have recently emerged. However, the increasing risk of automotive cybersecurity due to the vulnerability of electronic control units (ECUs) and automotive networks, which are essential for realizing the autonomous driving functions of smart cars, is a major obstacle to the widespread adoption of smart cars. Although there have been only a few real-world cases of smart car hacking, drivers' concerns about the security of smart cars can have a negative impact on their proliferation. Therefore, it is important to understand the risk factors perceived by drivers and the trust in smart cars formed through them in order to promote the future diffusion of smart cars. This study examines the risk factors that affect the formation of trust in smart cars, focusing on security and privacy, and analyzes how these factors affect safety perceptions and trust in smart cars.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.189-200
• /
• 2024

In recent years, the development of defense technology has become digital with the introduction of advanced assets such as drones equipped with artificial intelligence. These assets are integrated with modern information technologies such as industrial IoT, artificial intelligence, and cloud computing to promote innovation in the defense domain. However, the convergence of the technology is increasing the possibility of transfer of cyber threats, which is emerging as a problem of increasing the vulnerability of defense assets. While the current cybersecurity methodologies focus on the vulnerability of a single asset, interworking of various military assets is necessary to perform the mission. Therefore, this paper recognizes these problems and presents a mission-based asset management and evaluation methodology. It aims to strengthen cyber security in the defense sector by identifying assets that are important for mission execution and analyzing vulnerabilities in terms of cyber security. In this paper, we propose a method of classifying mission dependencies through linkage analysis between functions and assets to perform a mission, and identifying and classifying assets that affect the mission. In addition, a case study of identifying key assets was conducted through an attack scenario.

• Journal of Information Technology Services
• /
• v.23 no.1
• /
• pp.1-10
• /
• 2024

The IT environment is changing due to the acceleration of digital transformation in enterprises and organizations. This expansion of the digital space makes centralized cybersecurity controls more difficult. For this reason, cyberattacks are increasing in frequency and severity and are becoming more sophisticated, such as ransomware and digital supply chain attacks. Even in large organizations with numerous security personnel and systems, security incidents continue to occur due to unmanaged and unknown threats and vulnerabilities to IT assets. It's time to move beyond the current focus on detecting and responding to security threats to managing the full range of cyber risks. This requires the implementation of asset Inventory for comprehensive management by collecting and integrating all IT assets of the enterprise and organization in a wide range. IT Asset Management(ITAM) systems exist to identify and manage various assets from a financial and administrative perspective. However, the asset information managed in this way is not complete, and there are problems with duplication of data. Also, it is insufficient to update of data-set, including Network Infrastructure, Active Directory, Virtualization Management, and Cloud Platforms. In this study, we, the researcher group propose a new framework for automated 'Comprehensive IT Asset Management(CITAM)' required for security operations by designing a process to automatically collect asset data-set. Such as the Hostname, IP, MAC address, Serial, OS, installed software information, last seen time, those are already distributed and stored in operating IT security systems. CITAM framwork could classify them into unique device units through analysis processes in term of aggregation, normalization, deduplication, validation, and integration.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.9-17
• /
• 2024

This paper examines the security threats to enterprise Generative Artificial Intelligence systems and proposes countermeasures. As AI systems handle vast amounts of data to gain a competitive edge, security threats targeting AI systems are rapidly increasing. Since AI security threats have distinct characteristics compared to traditional human-oriented cybersecurity threats, establishing an AI-specific response system is urgent. This study analyzes the importance of AI system security, identifies key threat factors, and suggests technical and managerial countermeasures. Firstly, it proposes strengthening the security of IT infrastructure where AI systems operate and enhancing AI model robustness by utilizing defensive techniques such as adversarial learning and model quantization. Additionally, it presents an AI security system design that detects anomalies in AI query-response processes to identify insider threats. Furthermore, it emphasizes the establishment of change control and audit frameworks to prevent AI model leakage by adopting the cyber kill chain concept. As AI technology evolves rapidly, by focusing on AI model and data security, insider threat detection, and professional workforce development, companies can improve their digital competitiveness through secure and reliable AI utilization.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.131-139
• /
• 2023

In recent years, there have been frequent incidents of invasion of national defense networks by insiders. This trend can be said to disprove that the physical network separation policy currently applied by the Korea Ministry of National Defense can no longer guarantee military cyber security. Therefore, stronger cybersecurity measures are needed. In this regard, Zero Trust with a philosophy of never trusting and always verifying is emerging as a new alternative security paradigm. This paper analyzes the zero trust establishment trends currently being pursued by the US Department of Defense, and based on the implications derived from this, proposes a zero trust establishment plan tailored to the Korean military. The zero trust establishment plan tailored to the Korean military proposed in this paper includes a zero trust establishment strategy, a plan to organize a dedicated organization and secure budget, and a plan to secure zero trust establishment technology. Compared to cyber security based on the existing physical network separation policy, it has several advantages in terms of cyber security.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.21-29
• /
• 2024

With the development of ICT and network, security management of IT infrastructure that has grown in size is becoming very difficult. Many companies and public institutions are having difficulty managing system and network security. In addition, as the complexity of hardware and software grows, it is becoming almost impossible for a person to manage all security. Therefore, AI is essential for network security management. However, since it is very dangerous to operate an attack model in a real network environment, cybersecurity emulation research was conducted through reinforcement learning by implementing a real-life network environment. To this end, this study applied reinforcement learning to the network environment, and as the learning progressed, the agent accurately identified the vulnerability of the network. When a network vulnerability is detected through AI, automated customized response becomes possible.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.71-82
• /
• 2024

With the advancement of information and communication technology (ICT), the use of electronic document types such as PDF, MS Office, and HWP files has increased. Such trend has led the cyber attackers increasingly try to spread malicious documents through e-mails and messengers. To counter such attacks, AI-based methodologies have been actively employed in order to detect malicious document files. The main challenge in detecting malicious HWP(Hangul Word Processor) files is the lack of quality dataset due to its usage is limited in Korea, compared to PDF and MS-Office files that are highly being utilized worldwide. To address this limitation, data augmentation have been proposed to diversify training data by transforming existing dataset, but as the usefulness of the augmented data is not evaluated, augmented data could end up harming model's performance. In this paper, we propose an effective semi-supervised learning technique in detecting malicious HWP document files, which improves overall AI model performance via quantifying the utility of augmented data and filtering out useless training data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.667-680
• /
• 2024

If the software is not updated after the vulnerability is disclosed, it can continue to be attacked. As a result, the importance of N-day detection is increasing as attacks that exploit vulnerabilities increase. However, there is a problem that it is difficult to find specific version information in the published vulnerability database, or that the wrong version or software is outputted. There is also a limitation in that the connection between the published vulnerability databases is not good. In order to overcome these limitations, this paper proposes a method of building information including comprehensive vulnerability information such as CVE, CPE, and Exploit Database into an integrated database. Furthermore, by developing a website for searching for vulnerabilities based on an integrated database built as a result of this study, it is effective in detecting and utilizing vulnerabilities in specific software versions and Windows operating systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.707-724
• /
• 2024

Recently, Golang has been gaining attention in programming language rankings each year due to its cross-compilation capabilities and high code productivity. However, malware developers have also been increasingly using it to distribute malware such as ransomware and backdoors. Interestingly, Golang, being an open-source language, frequently changes the important values and configuration order of a crucial structure called Pclntab, which includes essential values for recovering deleted symbols whenever a new version is released. While frequent structural changes may not be an issue from a developer's perspective aiming for better code readability and productivity, it poses challenges in cybersecurity, as new versions with modified structures can be exploited in malware development. Therefore, this paper proposes GoAsap, a detection and analysis system for Golang executables targeting the new versions, and validates the performance of the proposed system by comparing and evaluating it against six existing binary analysis tools.