Detecting Zero-Day Attacks Using Contextual Relations

摘要: The focus of this research is a knowledge-based intrusion detection technique that utilizes contextual relations between known attacks to identify zero-day attacks, which are exploits unknown software vulnerabilities. proposed uses information entropy and linear data transformation generate feature-based function-based attack profiles. It systematically creates relationships profiles capture most likely combinations activities an attacker might exploit initiate attacks. We utilize the similarity among features incoming network connections these discover Our experiments on benchmark datasets indicate utilizing leads satisfactory rate from at different levels granularity.