Firmware Attack Detection Using Logistic Regression (FAD-LR)

DOI

10.2991/978-94-6463-250-7_8How to use a DOI?

Keywords

Internet - of - Things; Firmware; API calls; Logistic Regressionm; Machine Learning; Backdoors; Malware

Abstract

The smart devices, commonly referred to as IoT devices, are experiencing a significant surge in demand and are becoming increasingly integrated into our daily lives. Cyber felons perceive monetary potential, thereby intensifying and setting apart their assaults. One of the risks faced by IoT device enthusiasts is that threats can arise unexpectedly, and seemingly harmless methods can turn into powerful tools for illegal activities. Possible paraphrased text: - Crypto currency could be subject to hostile withdrawals, DDoS attacks, or botnet schemes that expose computers to harm. - Perils for crypto currency users may include malicious withdrawals, DDoS assaults, or botnets that exploit vulnerabilities in computer systems. - Risks to cryptocurrencies could entail malevolent withdrawals, DDoS offensives, or botnet activities that expose devices to compromise. - Threats to digital coins might involve harmful withdrawals, DDoS attacks, or botnet campaigns that compromise the security of computers. - Challenges facing virtual currency could involve malicious withdrawals, DDoS strikes, or botnet activities that compromise the confidentiality of computing devices. Once the IoT system belonging to the victim is infiltrated, the malwares seize command of the device and engage in malevolent actions. In this paper, the LR classification technique is suggested to cluster IoT app service calls to kernel API calls that are related to network. By utilizing LR, the pool network connected unidentified executable API calls that executed malicious activities specifically targeting IoT devices. After setting up the IoT kernel’s network of API calls, a LR algorithm was utilized to identify the closest association to the harmful behavior. The study involved evaluating 1621 malware specimens, derived from diverse sources and representing all malware groups, yielding an optimistic precision rating of 99.39% and a false positive rate of 0.1%.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - A. Punidha
AU  - E. Arul
AU  - E. Yuvarani
PY  - 2023
DA  - 2023/10/17
TI  - Firmware Attack Detection Using Logistic Regression (FAD-LR)
BT  - Proceedings of the 6th International Conference on Intelligent Computing (ICIC-6 2023)
PB  - Atlantis Press
SP  - 37
EP  - 41
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-250-7_8
DO  - 10.2991/978-94-6463-250-7_8
ID  - Punidha2023
ER  -