Attack Tree Analysis for Adversarial Evasion Attacks

Recently, the evolution of deep learning has promoted the application of machine learning (ML) to various systems. However, there are ML systems, such as autonomous vehicles, that cause critical damage when they misclassify. Conversely, there are ML-specific attacks called adversarial attacks based on the characteristics of ML systems. For example, one type of adversarial attack is an evasion attack, which uses minute perturbations called "adversarial examples" to intentionally misclassify classifiers. Therefore, it is necessary to analyze the risk of ML-specific attacks in introducing ML base systems. Unfortunately, there are few methods to analyze evasion attacks. In this study, we propose a quantitative evaluation method for analyzing the risk of evasion attacks using attack trees. The proposed method consists of the extension of the conventional attack tree to analyze evasion attacks and the systematic construction method of the extension. Finally, we conducted experiments on three ML image recognition systems to demonstrate the versatility and effectiveness of our proposed method.