- With cybersecurity concerns at an all time high, researchers have developed a method to defend Artificial Intelligence from adversarial cyber-attack variations https://www.mdpi.com/1999-5903/14/4/108 6 comments science
Linked pages
- [1710.08864] One pixel attack for fooling deep neural networks https://arxiv.org/abs/1710.08864 147 comments
- Creative Commons — Attribution 4.0 International — CC BY 4.0 https://creativecommons.org/licenses/by/4.0/ 95 comments
- [1707.05373] Houdini: Fooling Deep Structured Prediction Models https://arxiv.org/abs/1707.05373 0 comments