Intriguing properties of robust classification

Prach B, Lampert C. Intriguing properties of robust classification. arXiv, 2412.04245.

Download
No fulltext has been uploaded. References only!

Preprint | Submitted | English

Corresponding author has ISTA affiliation

Abstract
Despite extensive research since the community learned about adversarial examples 10 years ago, we still do not know how to train high-accuracy classifiers that are guaranteed to be robust to small perturbations of their inputs. Previous works often argued that this might be because no classifier exists that is robust and accurate at the same time. However, in computer vision this assumption does not match reality where humans are usually accurate and robust on most tasks of interest. We offer an alternative explanation and show that in certain settings robust generalization is only possible with unrealistically large amounts of data. More precisely we find a setting where a robust classifier exists, it is easy to learn an accurate classifier, yet it requires an exponential amount of data to learn a robust classifier. Based on this theoretical result, we explore how well robust classifiers generalize on datasets such as CIFAR-10. We come to the conclusion that on this datasets, the limitation of current robust models also lies in the generalization, and that they require a lot of data to do well on the test set. We also show that the problem is not in the expressiveness or generalization capabilities of current architectures, and that there are low magnitude features in the data which are useful for non-robust generalization but are not available for robust classifiers.
Publishing Year
Date Published
2024-12-05
Journal Title
arXiv
Article Number
2412.04245
IST-REx-ID

Cite this

Prach B, Lampert C. Intriguing properties of robust classification. arXiv. doi:10.48550/arXiv.2412.04245
Prach, B., & Lampert, C. (n.d.). Intriguing properties of robust classification. arXiv. https://doi.org/10.48550/arXiv.2412.04245
Prach, Bernd, and Christoph Lampert. “Intriguing Properties of Robust Classification.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2412.04245.
B. Prach and C. Lampert, “Intriguing properties of robust classification,” arXiv. .
Prach B, Lampert C. Intriguing properties of robust classification. arXiv, 2412.04245.
Prach, Bernd, and Christoph Lampert. “Intriguing Properties of Robust Classification.” ArXiv, 2412.04245, doi:10.48550/arXiv.2412.04245.

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 2412.04245

Search this title in

Google Scholar