Although deep neural networks have been very successful in image-classification tasks, they are prone to adversarial attacks. To generate adversarial inputs, there has emerged a wide variety of techniques, such as black- and whitebox attacks for neural networks. In this paper, we present DeepSearch, a novel fuzzing-based, query-efficient, blackbox attack for image classifiers. Despite its simplicity, DeepSearch is shown to be more effective in finding adversarial inputs than state-of-the-art blackbox approaches. DeepSearch is additionally able to generate the most subtle adversarial inputs in comparison to these approaches.
@article{arxiv.1910.06296,
title = {DeepSearch: A Simple and Effective Blackbox Attack for Deep Neural Networks},
author = {Fuyuan Zhang and Sankalan Pal Chowdhury and Maria Christakis},
journal= {arXiv preprint arXiv:1910.06296},
year = {2020}
}