• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.603-606
• /
• 2023

인공지능 (AI) 서비스는 현대 사회에서 중요한 역할을 맡고 있다. 그러나 이러한 서비스는 보안과 관련된 문제들을 가지고 있다. 본 논문은 AI 서비스의 보안과 관련된 문제와 해결책을 조사하고자 한다. AI 서비스의 개요와 대표적인 상용 서비스를 간략히 소개 후, AI 서비스에서 발생할 수 있는 보안상의 문제와 Chat GPT를 중심으로 한 보안 문제에 대해 다루고자 한다. 또한, 향후 AI보안 서비스 연구 분야와 적재적 기계학습 연구에 대한 전망을 살펴볼 예정이다. 이를 통해 안전하고 신뢰성 있는 AI 서비스를 제공하는데 기여하고자 한다.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.167-176
• /
• 2024

Chatbot services are used in various fields in connection with AI services. Security research on AI is also in its infancy, but research on practical security in the service implementation stage using it is more insufficient. This paper analyzes the security requirements for chatbot services linked to AI services. First, the paper analyzes the recently published papers and articles on AI security. A general implementation model is established by investigating chatbot services provided in the market. The implementation model includes five components including a chatbot management system and an AI engine Based on the established model, the protection assets and threats specialized in Chatbot services are summarized. Threats are organized around threats specialized in chatbot services through a survey of chatbot service managers in operation. Ten major threats were drawn. It derived the necessary security areas to cope with the organized threats and analyzed the necessary security requirements for each area. This will be used as a security evaluation criterion in the process of reviewing and improving the security level of chatbot service.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.577-589
• /
• 2023

Ministry of National Defense plans to harness AI as a key technology to bolster overall defense capability for cultivation of an advanced strong military based on science and technology based on Defense Innovation 4.0 Plan. However, security threats due to the characteristics of AI can be a real threat to AI-based defense information system. In order to solve them, systematic security activities must be carried out from the development stage. This paper proposes security activities and considerations that must be carried out at each stage of AI-based defense information system. Through this, It is expected to contribute to preventing security threats caused by the application of AI technology to the defense field and securing the safety and reliability of defense information system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.452-454
• /
• 2021

Currently, the security control market is operating based on AI technology. The reason for using AI is to detect large amounts of logs and big data between security equipment, and to alleviate time and human problems. However, problems are still occurring in the application of AI. The security control market is responding to many problems other than the problems introduced in this paper, and this paper attempts to deal with five problems. We would like to consider problems that arise in applying AI technology to security control environments such as 'AI model selection', 'AI standardization problem', 'Big data accuracy', 'Security Control Big Data Accuracy and AI Reliability', 'responsibility material problem', and 'lack of AI validity.'

• Review of KIISC
• /
• v.26 no.2
• /
• pp.35-38
• /
• 2016

본 논문에서는 핀테크 보안에 활용 가능한 딥러닝 기술을 살펴본다. 먼저 인공지능과 관련된 보안 이슈를 인공지능이 사람을 위협하는 상황에 대한 보안(Security FROM AI), 인공지능 시스템이나 서비스를 악의적인 공격으로부터 보호하는 이슈(Security OF AI), 인공지능 기술을 활용해 보안 문제를 해결하는 것(Security BY AI) 3가지로 구분하여 살펴본다. Security BY AI의 일환으로 딥러닝에 기반한 비정상탐지(anomaly detection)과 회귀분석(regression)기법을 설명하고, 이상거래탐지, 바이오인증, 피싱, 파밍 탐지, 본인확인, 명의도용탐지, 거래 상대방 신뢰도 분석 등 핀테크 보안 문제에 활용할 수 있는 방안을 살펴본다.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2023.11a
• /
• pp.329-330
• /
• 2023

인공지능(AI)은 지방자치단체 청사의 물리적 보안 시스템을 개선하는 데 활용될 수 있는 유망한 기술이다. 방대한 데이터를 분석하고 패턴을 식별할 수 있어, 테러나 폭력과 같은 위협을 사전에 예방하는데 도움이 될 수 있다. 또한, 인공지능(AI)은 실시간으로 보안 상황을 모니터링하고 이상 징후를 감지할 수 있어, 보안 인력의 업무 효율성을 향상시키고 비용을 절감하는 데에도 도움이 되기에 인공지능(AI)을 적용한 물리적 보안 시스템 개선방안에 대해 제안하고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.428-434
• /
• 2020

Recently, due to the development of ICT technology, changes to the convergence service platform of information systems are accelerating. Convergence services expanded to cyber systems with 5G communication, IoT, AI, and cloud are being reflected in the real world. However, the field of cybersecurity audit for responding to cyber attacks and security threats and strengthening security technology is insufficient. In this paper, we analyze the international standard analysis of information security management system, security audit analysis and security of related systems according to the expansion of 5G communication, IoT, AI, Cloud based information system security. In addition, we design and study cybersecurity audit checklists and contents for expanding security according to cyber attack and security threat of information system. This study will be used as the basic data for audit methods and audit contents for coping with cyber attacks and security threats by expanding convergence services of 5G, IoT, AI, and Cloud based systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1523-1537
• /
• 2018

The AI speaker is a simple operation that provides users with useful functions such as music playback, online search, and so the AI speaker market is growing at a very fast pace. However, AI speakers always wait for the user's voice, which can cause serious problems such as eavesdropping and personal information exposure if exposed to security threats. Therefore, in order to provide overall improved security of all AI speakers, it is necessary to identify potential security threats and analyze them systematically. In this paper, security threat modeling is performed by selecting four products with high market share. Data Flow Diagram, STRIDE and LINDDUN Threat modeling was used to derive a systematic and objective checklist for vulnerability checks. Finally, we proposed a method to improve the security of AI speaker by comparing the vulnerability analysis results and the vulnerability of each product.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.619-620
• /
• 2023

본 논문에서는 AI 모델이 노출될 수 있는 적대적 공격을 연구한 논문이다. AI 쳇봇이 적대적 공격에 노출됨에 따라 최근 보안 침해 사례가 다수 발생하고 있다. 이에 대해 본 논문에서는 적대적 공격이 무엇인지 조사하고 적대적 공격에 대응하거나 사전에 방어하는 방안을 연구하고자 한다. 적대적 공격의 종류 4가지와 대응 방안을 조사하고, AI 모델의 보안 중요성을 강조하고 있다. 또한, 이런 적대적 공격을 방어할 수 있도록 대응 방안을 추가로 조사해야 한다고 결론을 내리고 있다.