Traversing the subspace of adversarial patches

Abstract Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold hypothesis posits, high-dimensional data tends to be part of a low-dimensional manifold. To verify the thesis with adversarial patches–a special form of adversarial attack that can be used to fool object detectors in the physical world–this paper provides an analysis of a set of adversarial patches and investigates the reconstruction abilities of five different dimensionality reduction methods. Quantitatively, the performance of reconstructed patches in an attack setting is measured and the impact of sampled patches from the latent space during adversarial training is investigated. The evaluation is performed on two publicly available datasets for person detection. The results indicate that more sophisticated dimensionality reduction methods offer no advantages over a simple principal component analysis.