Goodfellow, 2015 — Explaining and Harnessing Adversarial Examples

DOI: <a href="https://doi.org/10.48550/arXiv.1412.6572" target="_blank" rel="noopener noreferrer">https://doi.org/10.48550/arXiv.1412.6572
URL: <a href="https://arxiv.org/abs/1412.6572" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/1412.6572

Introduces adversarial examples as evidence that learned models can fail under targeted perturbation.

Publication links

Introduces adversarial examples as evidence that learned models can fail under targeted perturbation.