New methods for explainable variational autoencoders

Riley White; Brian Baracat-Donovan; John Helmsen; Thomas McCullough

doi:10.1117/12.2680290

17 October 2023 New methods for explainable variational autoencoders

Riley White, Brian Baracat-Donovan, John Helmsen, Thomas McCullough

Proceedings Volume 12742, Artificial Intelligence for Security and Defence Applications; 127420J (2023) https://doi.org/10.1117/12.2680290
Event: SPIE Security + Defence, 2023, Amsterdam, Netherlands

Abstract

A new deep learning algorithm for performing anomaly detection and multi-class classification with explainability using counterfactuals is described. The system is a Variational Autoencoder (VAE) with a modified loss function and new methods for counterfactual identification. An additional hinge-loss term is added to VAE training. This enables convenient synthetic data generation and allows straightforward construction of multi-class counterfactuals. Counterfactuals are synthetic data generated to explain system decisions by answering the question: “If this data was not anomalous or was in another class, what modifications would need to be made?” To determine counterfactuals, a path is determined through the embedding space via adversarial attack-like techniques to minimize reconstruction error, with the restriction of minimally altering the number of columns changed. Large changes are allowed, unlike adversarial attack approaches, so changes are isolated and easily visible. Anomaly detection is performed by modifying a result to lower its anomalousness. Classification changes are performed by modifying the data to another class. Multi-class classification is performed on the embedding space of the VAE via an attached linear support vector machine (SVM). By adding the hinge-loss term to the VAE embedding training as well as the SVM, the embedding is modified to prefer class separation without being informed of the specific class labels. This causes the classes in the embedding space to be separated by hyperplanes, making counterfactual generation convenient and SVM classification accurate. Accuracy is shown to be comparable to other deep learners. Approaches to accommodating the image and time-series data are discussed.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Riley White, Brian Baracat-Donovan, John Helmsen, and Thomas McCullough "New methods for explainable variational autoencoders", Proc. SPIE 12742, Artificial Intelligence for Security and Defence Applications, 127420J (17 October 2023); https://doi.org/10.1117/12.2680290

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available