Automatic Evaluation and Signature Generation Technique for Thwarting Zero-Day Attacks

Abstract

Zero-day attack is a cyber-attack which exploits vulnerabilities that have not been disclosed publicly. Zero-day attacks are very expensive and powerful attack tools. They are used in conjunction with highly sophisticated and targeted attacks to achieve stealthiness with respect to standard intrusion detection techniques. Zero-day attacks are unknown and have no signature so they are difficult to detect. This paper presents a novel and efficient technique for detecting zero-day attacks. The proposed technique detects obfuscated zero-day attacks with two-level evaluation, generates signature for new attack automatically and updates other sensors by using push technology via global hotfix feature.