Back to Search
Start Over
Towards unlocking the mystery of adversarial fragility of neural networks
- Publication Year :
- 2024
-
Abstract
- In this paper, we study the adversarial robustness of deep neural networks for classification tasks. We look at the smallest magnitude of possible additive perturbations that can change the output of a classification algorithm. We provide a matrix-theoretic explanation of the adversarial fragility of deep neural network for classification. In particular, our theoretical results show that neural network's adversarial robustness can degrade as the input dimension $d$ increases. Analytically we show that neural networks' adversarial robustness can be only $1/\sqrt{d}$ of the best possible adversarial robustness. Our matrix-theoretic explanation is consistent with an earlier information-theoretic feature-compression-based explanation for the adversarial fragility of neural networks.<br />Comment: 21 pages
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2406.16200
- Document Type :
- Working Paper