DeepSearch: a simple and effective blackbox attack for deep neural networks
Fuyuan Zhang, Sankalan Pal Chowdhury, Maria Christakis
Abstract
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.
Topics & Concepts
Adversarial systemComputer scienceFuzz testingDeep neural networksSimplicityArtificial neural networkArtificial intelligenceVariety (cybernetics)Image (mathematics)Simple (philosophy)Machine learningState (computer science)Deep learningSoftwareAlgorithmProgramming languageEpistemologyPhilosophyAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsDomain Adaptation and Few-Shot Learning