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 \textsf{DeepSearch}\xspace, a novel fuzzing-based, query-efficient, blackbox attack for image
classifiers. Despite its
simplicity, \textsf{DeepSearch}{} is shown to be more effective in finding adversarial
inputs than state-of-the-art blackbox approaches. \textsf{DeepSearch}{} is
additionally able to generate the most subtle adversarial inputs in comparison to
these approaches.