2 papers
cs.SE2023
Don't Lie to Me: Avoiding Malicious Explanations with STEALTH
Lauren Alvarez, Tim Menzies
STEALTH is a method for using some AI-generated model, without suffering from malicious attacks (i.e. lying) or associated unfairness issues. After recursively bi-clustering the da…
cs.LG2022
A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
Guanqin Zhang, Jiankun Sun, Feng Xu +4
Deep neural networks (DNNs), are widely used in many industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, prior work has shown th…