Journal of Information Technology Services (한국IT서비스학회지)

Korea Society of IT Services (한국IT서비스학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Comparison of Machine Learning Algorithms for Network Traffic Security in Medical Equipment

의료기기 네트워크 트래픽 보안 관련 머신러닝 알고리즘 성능 비교

  • 고승형 (차의과학대학교 의학전문대학원 정보의학교실) ;
  • 박준호 (차의과학대학교 의학전문대학원 정보의학교실) ;
  • 왕다운 (차의과학대학교 의학전문대학원 정보의학교실) ;
  • 강은석 (차의과학대학교 의학전문대학원 정보의학교실) ;
  • 한현욱 (차의과학대학교 의학전문대학원 정보의학교실)
  • Received : 2023.07.05
  • Accepted : 2023.10.14
  • Published : 2023.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

As the computerization of hospitals becomes more advanced, security issues regarding data generated from various medical devices within hospitals are gradually increasing. For example, because hospital data contains a variety of personal information, attempts to attack it have been continuously made. In order to safely protect data from external attacks, each hospital has formed an internal team to continuously monitor whether the computer network is safely protected. However, there are limits to how humans can monitor attacks that occur on networks within hospitals in real time. Recently, artificial intelligence models have shown excellent performance in detecting outliers. In this paper, an experiment was conducted to verify how well an artificial intelligence model classifies normal and abnormal data in network traffic data generated from medical devices. There are several models used for outlier detection, but among them, Random Forest and Tabnet were used. Tabnet is a deep learning algorithm related to receive and classify structured data. Two algorithms were trained using open traffic network data, and the classification accuracy of the model was measured using test data. As a result, the random forest algorithm showed a classification accuracy of 93%, and Tapnet showed a classification accuracy of 99%. Therefore, it is expected that most outliers that may occur in a hospital network can be detected using an excellent algorithm such as Tabnet.

Keywords

Acknowledgement

이 논문은 2023년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(No.2019-0-00224, AIM : AI 기반 차세대 보안 정보관리기법적용 Cognitive Intelligence 및 Secure-오픈 프레임워크(S-OFW)기술 개발).

References

  1. 권혁찬, 정병호, 문대성, 김익균, "커넥티드 의료기기 해킹 및 랜섬웨어 대응기술 동향", 전자통신동향분석, 제36권, 제5호, 2021, 21-31. https://doi.org/10.22648/ETRI.2021.J.360503
  2. 김강현, 정성수, 한현욱. "딥러닝 기반 병원네트워크 이상행위 탐지 시스템에 관한 연구", 한국통신학회 학술대회논문집, 2022, 490-491.
  3. 김기환, 최성수, 김일환, 신용태, "디지털헬스케어 차세대 정보보호체계수립방안에 대한 연구", 한국컴퓨터정보학회논문지, 제27권, 제7호, 2022, 57-64. https://doi.org/10.9708/JKSCI.2022.27.07.057
  4. 우성희, 이효정, "IoMT 기술과 의료정보 보안", 한국정보통신학회 종합학술대회 논문집, 제25권, 제1호, 2021, 641-643.
  5. 이식, 김동훈, 조영훈, 명준우, 문다민, 이재구, 윤명근, "머신러닝 기반 보안데이터 분석 연구", 정보보호학회지, 제29권, 제3호, 2019, 6-13.
  6. 최성호, 곽진, "국외 의료기기 보안위협 사례 및 보안동향 조사", 정보보호학회지, 제25권, 제3호, 2015, 11-18.
  7. Alosaimi, S. and S.M. Almutairi, "An Intrusion Detection System Using BoT-IoT", Applied Sciences, Vol.13, No.9, 2023, 5427.
  8. Arik, S.O. and T. Pfister, "TabNet: Attentive Interpretable Tabular Learning", Proceedings of the AAAI Conference on Artificial Intelligence, Vol.35, No.9, 2021, 6679-6687.
  9. Bradley, A.P., "The use of the area under the ROC curve in the evaluation of machine learning algorithms", Pattern Recognition, Vol.30, No.7, 1997, 1145-1159. https://doi.org/10.1016/S0031-3203(96)00142-2
  10. Random forest, Available at http://www.incodom.kr/Random_Forest (Accessed August, 10. 2023).
  11. Flach P., J. Hernandez-Orallo, and C. Ferri, "A Coherent Interpretation of AUC as a Measure of Aggregated Classification Performance", Proceedings of the 28th International Conference on International Conference on Machine Learning, 2011, 657-664.
  12. Ho, T. K., "Random Decision Forest", Proceedings of the 3rd International Conference on Document Analysis and Recognition, 1995, 278-282.
  13. Kumar, M., A. Kumar, S. Verma, P. Bhattacharya, D. Ghimire, S.-H. Kim, A.S.M.S. Hosen, "Healthcare Internet of Things (H-IoT): Current Trends, Future Prospects, Applications, Challenges, and Security Issues", Electronics, Vol.12, No.9, 2023, 1-19. https://doi.org/10.3390/electronics12092050
  14. Lipton, Z.C., C. Elkan, and B. Narayanaswamy, "Thresholding Classifiers to Maximize F1 Score", 2014, Available at https://arxiv.org/pdf/1402.1892.pdf (Accessed August, 10. 2023).
  15. Machine learning-based NIDS 데이터 세트, 2020, Available at https://staff.itee.uq.edu.au/marius/NIDS_데이터 세트/ (Accessed August, 10. 2023).
  16. Official pyTorch TabNet, Availabel at https://github.com/dreamquark-ai/tabnet (Accessed August, 10. 2023).
  17. Yang, T. and Y. Ying, "AUC Maximization in the Era of Big Data and AI: A Survey", 2022, Availabe at https://arxiv.org/abs/2203.15046 (Accessed August, 10. 2023).