Towards an Interpretable Autoencoder: A Decision-Tree-Based Autoencoder and its Application in Anomaly Detection

The importance of understanding and explaining the associated classification results in the utilization of artificial intelligence (AI) in many different practical applications (e.g., cyber security and forensics) has contributed to the trend of moving away from black-box / opaque AI towards explain...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on dependable and secure computing Vol. 20; no. 2; pp. 1048 - 1059
Main Authors: Aguilar, Diana Laura, Medina-Perez, Miguel Angel, Loyola-Gonzalez, Octavio, Choo, Kim-Kwang Raymond, Bucheli-Susarrey, Edoardo
Format: Journal Article
Language:English
Published: Washington IEEE 01.03.2023
IEEE Computer Society
Subjects:
Algorithms
Anomalies
Anomaly detection
Artificial intelligence
autoencoder
Computational modeling
Computer architecture
Cybersecurity
decision tree
Decision trees
Decoding
Encoding
Explainable artificial intelligence
explainable artificial intelligence (XAI)
Interpretable artificial intelligence
Neural networks
Outliers (statistics)
Probabilistic models
Support vector machines
ISSN:1545-5971, 1941-0018
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The importance of understanding and explaining the associated classification results in the utilization of artificial intelligence (AI) in many different practical applications (e.g., cyber security and forensics) has contributed to the trend of moving away from black-box / opaque AI towards explainable AI (XAI). In this article, we propose the first interpretable autoencoder based on decision trees, which is designed to handle categorical data without the need to transform the data representation. Furthermore, our proposed interpretable autoencoder provides a natural explanation for experts in the application area. The experimental findings show that our proposed interpretable autoencoder is among the top-ranked anomaly detection algorithms, along with one-class Support Vector Machine (SVM) and Gaussian Mixture. More specifically, our proposal is on average 2% below the best Area Under the Curve (AUC) result and 3% over the other Average Precision scores, in comparison to One-class SVM, Isolation Forest, Local Outlier Factor, Elliptic Envelope, Gaussian Mixture Model, and eForest.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-5971
1941-0018
DOI:10.1109/TDSC.2022.3148331