Internet Archive Scholar
Filters
























1 Hit in 2.7 sec

Constraining Logits by Bounded Function for Adversarial Robustness [article]

Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi, Hiroshi Takahashi, Yasutoshi Ida
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (5.7 MB)
https://web.archive.org/web/20201008013140/https://arxiv.org/pdf/2010.02558v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

The addition of our function improves adversarial robustness because it makes logit and pre-logit vectors have small norms.  ...  Following this hypothesis, we analyze norms of logit vectors at the optimal point under the assumption of universal approximation and explore new methods for constraining logits by addition of a bounded  ...  Batch-wise Logit-Similarity: Generalizing Logit-Squeezing and Label-Smoothing. In Proc. BMVC. Summers, C.; and Dinneen, M. J. 2019.  ... 
arXiv:2010.02558v1 fatcat:q5sru4ziojf73b4fho2qfmvh2i
Citation

Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi, Hiroshi Takahashi, Yasutoshi Ida. "Constraining Logits by Bounded Function for Adversarial Robustness." arXiv (2020)