Chan Ho Shin, Chang-hee Choi, Journal of Internet Computing and Services, Vol. 23, No. 6, pp. 15-26, Dec. 2022
10.7472/jksii.2022.23.6.15, Full Text:  HTML
Keywords: Labeling, Machine Learning, Deep Learning, MITRE ATT&CK, TTP, CIA triad

Abstract

Various subjects are carrying out cyberattacks using a variety of tactics and techniques. Additionally, cyberattacks for political and economic purposes are also being carried out by groups which is sponsored by its nation. To deal with cyberattacks, researchers used to classify the malware family and the subjects of the attack based on malware signature. Unfortunately, attackers can easily masquerade as other group. Also, as the attack varies with subject, techniques, and purpose, it is more effective for defenders to identify the attacker’s purpose and goal to respond appropriately. The essential goal of cyberattacks is to threaten the information security of the target assets. Information security is achieved by preserving the confidentiality, integrity, and availability of the assets. In this paper, we relabel the attacker’s goal based on MITRE ATT&CKⓇ in the point of CIA triad as well as classifying cyber security reports to verify the labeling method. Experimental results show that the model classified the proposed CIA label with at most 80% probability.

Statistics
Cite this article