Adversarial attacks detection based on an ontology of cyber threat

Abstract

Machine learning has been used in the field of cybersecurity to predict trends in cyberattacks. However, adversaries can inject malicious data into the dataset during training and testing to cause disruption and predict false narratives. It has become difficult to analyze and predict correlations of cyberattacks due to their fuzzy nature and lack of understanding of the nature of threats. We use our model to create a cyber threat ontology and use its rules to detect adversarial machine learning attacks. Keywords: Cyber security, cyber attacks, cyber defense, machine learning, adversary attacks, cyber threat ontology.