Abstract

Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford’s law, as a method used to quantify the difference between real and corrupted inputs. We believe that in many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data. We hope to open a discussion on these applications and further areas where this technique is underexplored.

Original languageEnglish
Title of host publicationLecture Notes on Data Engineering and Communications Technologies
PublisherSpringer Science and Business Media Deutschland GmbH
Pages426-435
Number of pages10
DOIs
Publication statusPublished - 2023

Publication series

NameLecture Notes on Data Engineering and Communications Technologies
Volume164
ISSN (Print)2367-4512
ISSN (Electronic)2367-4520

Keywords

  • Anomaly detection
  • Benford’s law
  • Computer vision
  • Image corruption
  • Out-of-distribution data

Fingerprint

Dive into the research topics of 'On the Detection of Anomalous or Out-of-Distribution Data in Vision Models Using Statistical Techniques'. Together they form a unique fingerprint.

Cite this