Anomalous Example Detection in Deep Learning: A Survey

Saikiran Bulusu

doi:10.1109/ACCESS.2020.3010274

Anomalous Example Detection in Deep Learning: A Survey

2020-01-01

126

OA

AI

DOI：10.1109/ACCESS.2020.3010274

Original

Save

View PDF

Abstract

En 中文

Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications. We provide a taxonomy for existing techniques based on their underlying assumptions and adopted approaches. We discuss various techniques in each of the categories and provide the relative strengths and weaknesses of the approaches. Our goal in this survey is to provide an easier yet better understanding of the techniques belonging to different categories in which research has been done on this topic. Finally, we highlight the unsolved research challenges while applying anomaly detection techniques in DL systems and present some high-impact future research directions.

Keywords:

Anomaly detection

Machine learning

Training data

Data models

Training

Neural networks

Licenses

Anomaly detection

out-of-distribution

adversarial examples

deep learning

neural network

Anomalous Example Detection in Deep Learning: A Survey

Abstract

AI Summary

Journal

Organization