An Approach of Malware Detection in Power System. Issue 1 (1st December 2022)

• Record Type: Journal Article
• Authors: Han, Wei; Cai, Deyu; Du, Xingwei; Ma, Weidong; Guo, Pei; Wang, Feng; Wang, Shuzhou; Zhao, Zhibo
• Is Part Of: Journal of physics. Volume 2401 Issue 1(2022)
• Publication Date: 2022-12-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2401/1/012032
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In recent years, cyber attacks against the power industry have occurred frequently, causing huge losses to national infrastructure construction. As an important carrier of network attacks, malware has a great threat to the power system. This paper proposes an E-Gemini model based on the analysis of binary executable files and traditional malware detection techniques. This model was developed by Gemini [1] and has a stronger analysis ability for malware in power systems. This paper also alleviates the problem of the small size of the current power system malware dataset by pretraining and retraining. Experiments have verified the effectiveness of the E-Gemini model. The results show that the proposed model can achieve a maximum accuracy of 89%, which is significantly improved compared to the baseline method.