Machine learning application for malwares classification using visualization technique
Ikram Ben Abdel Ouahab, Mohammed Bouhorma, Boudhir Anouar Abdelhakim, El Aachak Lotfi, Bassam Abdulwahab Zafar · Proceedings of the 4th International Conference on Smart City Applications · 2019
Nowadays attackers work hard to develop efficient cyberthreats and exploit new techniques. So defenders need to use advanced methodologies to combat the latest threats and safely remove them from computers, mobiles and connected devices. Without the intelligent techniques, these devices would be at increased risk of damage from malicious programs. Recently a novel approach of processing malwares was appeared; it passes from malware binaries into malware images. Researchers found similarities in malwares images by extracting specific features. This paper presents malwares classifier using KNN and malware visualization technique. We used a database of 9339 samples of malwares from 25 families. We calculated the GIST descriptor for grayscale malware images. Then a KNN model was trained and evaluated many times to reach a score of 97%, which is very close to results found on literature.