4.6 Article

Anomalous Example Detection in Deep Learning: A Survey

Journal

IEEE ACCESS
Volume 8, Issue -, Pages 132330-132347

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3010274

Keywords

Anomaly detection; Machine learning; Training data; Data models; Training; Neural networks; Licenses; Anomaly detection; out-of-distribution; adversarial examples; deep learning; neural network

Funding

  1. U.S. Department of Energy by Lawrence Livermore National Laboratory [DE-AC52-07NA27344]

Ask authors/readers for more resources

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.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available