International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Malware Detector Classification Based on the SPRT in IoT

  • Jun-Won, Ho (Department of Information Security, Seoul Women‘s University)
  • Received : 2022.12.24
  • Accepted : 2022.12.29
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

We create a malware detector classification method with using the Sequential Probability Ratio Test (SPRT) in IoT. More specifically, we adapt the SPRT to classify malware detectors into two categories of basic and advanced in line with malware detection capability. We perform evaluation of our scheme through simulation. Our simulation results show that the number of advanced detectors is changed in line with threshold for fraction of advanced malware information, which is used to judge advanced detectors in the SPRT.

Keywords

Acknowledgement

This work was supported by a research grant from Seoul Women's University(2023-0001).

References

  1. E. Gandotra, D. Bansal and S. Sofat, "Zero-day malware detection," 2016 Sixth International Symposium on Embedded Computing and System Design (ISED), Patna, India, 2016, pp. 171-175, DOI: https://doi.org/10.1109/ISED.2016.7977076.
  2. A. Ravi and V. Chaturvedi, "Static Malware Analysis using ELF features for Linux based IoT devices," 2022 35th International Conference on VLSI Design and 2022 21st International Conference on Embedded Systems (VLSID), Bangalore, India, 2022, pp. 114-119, DOI: https://10.1109/VLSID2022.2022.00033.
  3. M. Ficco, "Detecting IoT Malware by Markov Chain Behavioral Models," 2019 IEEE International Conference on Cloud Engineering (IC2E), Prague, Czech Republic, 2019, pp. 229-234, DOI: https://10.1109/IC2E.2019.00037.
  4. A. Wald. Sequential Analysis, Dover, 2004.
  5. D. Kirat, G. Vigna, C. Kruegel. BareCloud: Bare-metal Analysis-based Evasive Malware Detection. In Usenix Security, 2014.