Timezone: »

 
Poster
Exploring the Landscape of Spatial Robustness
Logan Engstrom · Brandon Tran · Dimitris Tsipras · Ludwig Schmidt · Aleksander Madry

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #142
in Posters Wed »
The study of adversarial robustness has so far largely focused on perturbations bound in $\ell_p$-norms. However, state-of-the-art models turn out to be also vulnerable to other, more natural classes of perturbations such as translations and rotations. In this work, we thoroughly investigate the vulnerability of neural network--based classifiers to rotations and translations. While data augmentation offers relatively small robustness, we use ideas from robust optimization and test-time input aggregation to significantly improve robustness. Finally we find that, in contrast to the $\ell_p$-norm case, first-order methods cannot reliably find worst-case perturbations. This highlights spatial robustness as a fundamentally different setting requiring additional study.
Keywords: Adversarial Examples

Author Information

Logan Engstrom (MIT)
Brandon Tran (MIT)
Dimitris Tsipras (MIT)
Ludwig Schmidt (UC Berkeley)
Aleksander Madry (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors