Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks

November 03, 2020 ยท The Cartographer ยท ๐Ÿ› arXiv.org

๐Ÿ“š THE CARTOGRAPHER: The Cartographer
Survey/review paper โ€” maps the landscape rather than implementing a method.

"No code URL or promise found in abstract"
"Title-pattern auto-detect: Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks"

Evidence collected by the PWNC Scanner

Authors Tao Bai, Jinqi Luo, Jun Zhao arXiv ID 2011.01539 Category cs.LG: Machine Learning Cross-listed cs.CV Citations 9 Venue arXiv.org Last Checked 3 days ago
Abstract
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence score. It is increasingly important to obtain models with high robustness that are resistant to adversarial examples. In this paper, we survey recent advances in how to understand such intriguing property, i.e. adversarial robustness, from different perspectives. We give preliminary definitions on what adversarial attacks and robustness are. After that, we study frequently-used benchmarks and mention theoretically-proved bounds for adversarial robustness. We then provide an overview on analyzing correlations among adversarial robustness and other critical indicators of DNN models. Lastly, we introduce recent arguments on potential costs of adversarial training which have attracted wide attention from the research community.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning