Anomalous Example Detection in Deep Learning: A Survey
It synthesizes existing research to aid in making deep learning more robust, but is incremental as it reviews rather than introduces new methods.
This survey provides a structured overview of anomaly detection techniques for deep learning applications, categorizing methods based on assumptions and approaches to address vulnerabilities like out-of-distribution and adversarial examples.
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.