Adversarial Examples That Fool Both Computer Vision and Time-Limited Humans
Abstract
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recent techniques that transfer adversarial examples from computer vision models with known parameters and architecture to other models with unknown parameters and architecture, and by matching the initial processing of the human visual system. We find that adversarial examples that strongly transfer across computer vision models influence the classifications made by time-limited human observers.
Cite
Text
Elsayed et al. "Adversarial Examples That Fool Both Computer Vision and Time-Limited Humans." Neural Information Processing Systems, 2018.Markdown
[Elsayed et al. "Adversarial Examples That Fool Both Computer Vision and Time-Limited Humans." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/elsayed2018neurips-adversarial/)BibTeX
@inproceedings{elsayed2018neurips-adversarial,
title = {{Adversarial Examples That Fool Both Computer Vision and Time-Limited Humans}},
author = {Elsayed, Gamaleldin and Shankar, Shreya and Cheung, Brian and Papernot, Nicolas and Kurakin, Alexey and Goodfellow, Ian and Sohl-Dickstein, Jascha},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {3910-3920},
url = {https://mlanthology.org/neurips/2018/elsayed2018neurips-adversarial/}
}