Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems. We demonstrate the existence of robust 3D adversarial objects, and we present the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations. We synthesize two-dimensional adversarial images that are robust to noise, distortion, and affine transformation. We apply our algorithm to complex three-dimensional objects, using 3D-printing to manufacture the first physical adversarial objects. Our results demonstrate the existence of 3D adversarial objects in the physical world.
@article{arxiv.1707.07397,
title = {Synthesizing Robust Adversarial Examples},
author = {Anish Athalye and Logan Engstrom and Andrew Ilyas and Kevin Kwok},
journal= {arXiv preprint arXiv:1707.07397},
year = {2018}
}