Differences
This shows you the differences between two versions of the page.
|
papers [2019/10/21 21:07] 590ta |
papers [2019/10/24 19:37] (current) 590ta |
||
|---|---|---|---|
| Line 38: | Line 38: | ||
| *[[https://aclweb.org/anthology/P18-2006|HotFlip: White-Box Adversarial Examples for Text Classification]] | *[[https://aclweb.org/anthology/P18-2006|HotFlip: White-Box Adversarial Examples for Text Classification]] | ||
| *[[https://arxiv.org/pdf/1801.02610.pdf|Generating Adversarial Examples with Adversarial Networks]] | *[[https://arxiv.org/pdf/1801.02610.pdf|Generating Adversarial Examples with Adversarial Networks]] | ||
| + | *[[https://arxiv.org/pdf/1707.08945.pdf|Robust Physical-World Attacks on Deep Learning Models]] | ||
| *Backdoor attack and defense | *Backdoor attack and defense | ||
| *[[https://machine-learning-and-security.github.io/papers/mlsec17_paper_51.pdf|BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain]] | *[[https://machine-learning-and-security.github.io/papers/mlsec17_paper_51.pdf|BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain]] | ||
