Abstract

At Cyber Threat Intelligence (CTI), malware detection is one of the key tasks required for maintaining cybersecurity. We present in this paper an innovative technique using the Firefly Algorithm that offers cutting-edge intelligence techniques for malware detection and prevention in CTI environments. Our proposed approach combines the strengths of both algorithms to enhance malware detection. The Firefly Algorithm is employed for selecting dynamic features of malware samples that can improve the detection accuracy of samples by our cyber threat intelligence approach. Furthermore, PDF-Mal2022, MalMem2022, and MalDroid2022-based datasets are employed to test our proposed cyber threat intelligence approach. These datasets play an important role in facilitating comprehensive analysis and evaluation, enabling our approach to effectively tackle malware detection challenges across various platforms and file types. The proposed approach is evaluated and compared with several state-of-the-art malware detection methods. Experimental results demonstrate that our approach outperforms other methods in accuracy, precision, recall, and F1-score.