journalarticle

Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers

Jayaram Raghuram, Varun Chandrasekaran, S. Jha, Suman Banerjee

arXiv.org2020-07-29 8 citations79 references

Looking for the full paper…

Export

Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.

Abstract

No abstract is available from our sources. Use “Read paper” to view it.

TL;DRThis work proposes an unsupervised statistical testing framework for detecting anomalous inputs to a trained DNN classifier based on its internal layer representations, and provides an alternative class prediction that can be used to correct the DNNs prediction on (detected) adversarial inputs. (Semantic Scholar)

Plain-language summary

AI illustration of the topic of “Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers”

Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers

Abstract

Plain-language summary

Discussion