Anomalous Example Detection in Deep Learning: A Survey

Anomalous Example Detection in Deep Learning: A Survey

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...

Full description

Bibliographic Details
Main Authors: Saikiran Bulusu, Bhavya Kailkhura, Bo Li, Pramod K. Varshney, Dawn Song
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Anomaly detection
out-of-distribution
adversarial examples
deep learning
neural network
Online Access:https://ieeexplore.ieee.org/document/9144212/

Similar Items

Similar Items