Usage of Adversarial Examples as a Defensive Mechanism in Cybersecurity

Abstract

The focus of this research article is on defenses to a theoretical threat model of malware. The malware, or GUI-Attack, aims to search the victim computer’s desktop and use image recognition to find the icons for highly used web browsers such as Google Chrome, Internet Explorer, Mozilla Firefox, and Opera, and gain access to secure data and information. We propose that adversarial examples can be used as a defensive mechanism to protect secure information from these GUI-Attacks. We hope to prove that these adversarial examples can be used to prevent malicious AI from being able to recognize the icons for popular web browsers, making an effective defensive mechanism against AI-powered GUI-Attacks.