Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques for defending against adversarial examples. First, we propo...
| প্রধান লেখক: | , , , , |
|---|---|
| বিন্যাস: | প্রবন্ধ |
| ভাষা: | English |
| প্রকাশিত: |
Frontiers Media S.A.
2022-01-01
|
| মালা: | Frontiers in Artificial Intelligence |
| বিষয়গুলি: | |
| অনলাইন ব্যবহার করুন: | https://www.frontiersin.org/articles/10.3389/frai.2021.752831/full |