A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Gradient-Based Adversarial and Out-of-Distribution Detection
[article]
2022
arXiv
pre-print
We propose to utilize gradients for detecting adversarial and out-of-distribution samples. We introduce confounding labels -- labels that differ from normal labels seen during training -- in gradient generation to probe the effective expressivity of neural networks. Gradients depict the amount of change required for a model to properly represent given inputs, providing insight into the representational power of the model established by network architectural properties as well as training data.
arXiv:2206.08255v2
fatcat:os55tbr46zaitm2sen4pqmcz24