An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks

By R. Lapid et al.

Read the original document by opening this link in a new tab.

Table of Contents

I. Introduction\nII. Related Work\nIII. Threat Model\nIV. QueryAttack\nV. Experiments and Results

Summary

Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained model and receive an output. This paper introduces Query-Efficient Evolutionary Attack, QuEry Attack, an untargeted, score-based, black-box attack. QuEry Attack is based on a novel objective function that can be used in gradient-free optimization problems. The attack only requires access to the output logits of the classifier and is thus not affected by gradient masking. No additional information is needed, rendering our method more suitable to real-life situations. We test its performance with three different state-of-the-art models—Inception-v3, ResNet-50, and VGG-16-BN—against three benchmark datasets: MNIST, CIFAR10 and ImageNet. Furthermore, we evaluate QuEry Attack's performance on non-differential transformation defenses and state-of-the-art robust models. Our results demonstrate the superior performance of QuEry Attack, both in terms of accuracy score and query efficiency.