Malware Detection in Critical Infrastructure using Machine Learning

Main Article Content

Ashwini Kumar Verma, Sanjay Kumar Sharma

Abstract

Operational Technology (OT) play a crucial role in maintaining the safety and efficient operation of critical infrastructure across various industries. OT are vulnerable to various cyberthreats, including malware, which can have serious consequences for critical infrastructure. Malware refers to any type of malicious software that is intended harm and cause trouble. This may includes Virus, Worms, Trojan, Trojan-Downloader, Trojan-Dropper, and worms. In this paper portable executables of malware, usually found in the OT, which is front line of critical infrastructure, utilized by the parsing the header and extracting the 57 features in to the csv file. This data rich CSV file format is further used to apply machine learning algorithms- Linear Regression, Logistic Regression, SGD, Gaussion NB, Decision Tree, Random Forest, Adaboost, SVC, KNN, XG Boost and LGBM. The Random Forest model demonstrated an impressive 98.98% accuracy in detecting malware. The proposed approach provides valuable insights into the sophisticated methodologies employed for malware detection in OT, thereby enhancing cybersecurity measures in critical infrastructure sectors.

Article Details

Section
Articles