AI 기반 NIDS에 대한 모델 종류 추론 공격
Model Type Inference Attack against AI-Based NIDS
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
IoT 네트워크의 증가로 인해 사이버 공격도 함께 증가하고 있으며, 네트워크 침입탐지 시스템(NIDS)의 중요성이 강조되고 있다. 전통적인 NIDS의 한계를 극복하고 더욱 고도화된 사이버 공격에 대응하기 위해 NIDS에 인공지능 모델을 도입하는 추세이다. 인공지능 모델 기반의 NIDS는 인공지능 알고리즘이 가지는 적대적 공격에 대한 취약성을 가지게 된다. 모델 종류 추론 공격은 모델 내부의 정보를 추론하는 적대적 공격의 일종이다. 본 논문은 기존 모델 종류 추론 공격을 더욱 현실적인 가정을 적용하며, NIDS 모델을 타겟으로 최적화된 모델 종류 추론 공격 프레임워크를 제안한다. 제안하는 방식으로 NIDS 모델의 종류를 추론하는 공격 모델을 약 0.92의 분류 정확도를 보이도록 훈련할 수 있었으며, 인공지능 기반 NIDS에 대한 새로운 보안 위협을 제시하며 이에 대한 방어 기술 개발의 중요성을 강조한다.
Abstract
The proliferation of IoT networks has led to an increase in cyber attacks, highlighting the importance of Network Intrusion Detection Systems (NIDS). To overcome the limitations of traditional NIDS and cope with more sophisticated cyber attacks, there is a trend towards integrating artificial intelligence models into NIDS. However, AI-based NIDS are vulnerable to adversarial attacks, which exploit the weaknesses of algorithm. Model Type Inference Attack is one of the types of attacks that infer information inside the model. This paper proposes an optimized framework for Model Type Inference attacks against NIDS models, applying more realistic assumptions. The proposed method successfully trained an attack model to infer the type of NIDS models with an accuracy of approximately 0.92, presenting a new security threat to AI-based NIDS and emphasizing the importance of developing defence method against such attacks.
참고문헌 (28)
- M.K. Asif, "Network Intrusion Detection and its strategic importance", IEEE Business Engineering and Industrial Applications Colloquium (BEIAC), pp.140~144 (2013)
- D. Joo, "The neural network models for IDS based on the asymmetric costs of false negative errors and false positive errors", Expert Systems with Applications, 25(1), pp.69~75 (2003)
- B. Subba, "A Neural Network based system for Intrusion Detection and attack classification", Twenty Second National Conference on Communication (NCC), pp.1~6 (2016)
- M.S. Habeeb, "Network intrusion detection system: a survey on artificial intelligence‐based techniques", Expert Systems, 39(9) (2022)
- K. He, "Adversarial Machine Learning for Network Intrusion Detection Systems : A Comprehensive Survey", IEEE Communications Surveys & Tutorials, 25(1), pp.538~566 (2023)
- K. Yang, "Adversarial Examples Against the Deep Learning Based Network Intrusion Detection Systems", MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM), pp.559~564 (2018)
- "Explaining and Harnessing Adversarial Examples" (2015)[URL]
- Z. Tian, "A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning", ACM Computing Surveys, 55(8) (2022)
- S. Alahmed, "Impacting Robustness in Deep Learning-Based NIDS through Poisoning Attacks", MDPI Algorithms 2024, 17(4), pp.155~ (2024)
- "Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack" (2021)[URL]
- R. Shokri, "Membership Inference Attacks Against Machine Learning Models", 2017 IEEE Symposium on Security and Privacy (SP), pp.3~18 (2017)
- H. Qiu, "Adversarial Attacks Against Network Intrusion Detection in IoT Systems", IEEE Internet of Things Journal, 8(13), pp.10327~10335 (2021)
- C. Zhang, "Adversarial Attacks Against Deep Learning-Based Network Intrusion Detection Systems and Defense Mechanisms", IEEE, 2022, pp.30(3), 1294~1311
- Y. An, "Model Type Inference Attack Using Output of Black-Box AI Model", Journal of the Korea Institute of Information Security & Cryptology, 10(5), pp.817~826 (2022)
- K. Roshan, "Untargeted white-box adversarial attack with heuristic defence methods in real-time deep learning based network intrusion detection system", Computer Communications, 218, pp.97~113 (2024)
- D. Oliynyk, "I Know What You Trained Last Summer : A Survey on Stealing Machine Learning Models and Defences", ACM Computing Surveys, 55(14) (2023)
- A. Ilyas, "Black-box Adversarial Attacks with Limited Queries and Information", Proceedings of Machine Learning Research(PMLR), 80, pp.2137~2146 (2018)
- R. Vinayakumar, "Deep Learning Approach for Intelligent Intrusion Detection System", IEEE Access, 7, pp.41525~41550 (2019)
- M. Liu, "Host-Based Intrusion Detection System with System Calls : Review and Future Trends", ACM Computing Surveys, 51(5), pp.1~36 (2018)
- G.Kondrak, "N-Gram Similarity and Distance", Lecture Notes in Computer Science, 3772 (2005), Springer
- F. Zenke, "Continual Learning Through Synaptic Intelligence", Proceedings of the 34th International Conference on Machine Learning, 70, pp.3987~3995 (2017)
- M. Tavallaee, "A detailed analysis of the KDD CUP 99 data set", 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, pp.1~6 (2009)
- L. Dhanabal, "A study on NSL-KDD dataset for intrusion detection system based on classification algorithms", International Journal of Advanced Research in Computer and Communication Engineering, 4(6) (2015)
- M. Gao, "Malicious Network Traffic Detection Based on Deep Neural Networks and Association Analysis", MDPI Sensors, 20(5) (2020)
- A. Rosay, "Network Intrusion Detection: A Comprehensive Analysis of CIC-IDS2017", 8th International Conference on Information Systems Security and Privacy, pp.25~36 (2022)
- "Generating Practical Adversarial Network Traffic Flows Using NIDSGAN" (2022)[URL]
- J. Mirkovic, "A taxonomy of DDoS attack and DDoS defense mechanisms", ACM SIGCOMM Computer Communication Review, 34(2), pp.39~53 (2004)
- Z. Durumeric, "The Matter of Heartbleed", IMC '14: Proceedings of the 2014 Conference on Internet Measurement, pp.475~488 (2014)