Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning (2023)

First Author: Beerens L

Attributed to: Inference, COmputation and Numerics for Insights into Cities (ICONIC) funded by EPSRC

Abstract

No abstract provided

Bibliographic Information

Digital Object Identifier: http://dx.doi.org/10.48550/arxiv.2306.02918

Publication URI: https://arxiv.org/abs/2306.02918

Type: Preprint