Extracting explanations, justification, and uncertainty from black-box deep neural networks

Paul Ardis; Arjuna Flenner

doi:10.1117/12.3012765

7 June 2024 Extracting explanations, justification, and uncertainty from black-box deep neural networks

Paul Ardis, Arjuna Flenner

Proceedings Volume 13054, Assurance and Security for AI-enabled Systems; 1305405 (2024) https://doi.org/10.1117/12.3012765
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this paper, we propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from DNNs. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining, including applications to anomaly detection and out-of-distribution detection tasks. We validate our approach on the CIFAR-10 dataset, and show that it can significantly improve the interpretability and reliability of DNNs.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Paul Ardis and Arjuna Flenner "Extracting explanations, justification, and uncertainty from black-box deep neural networks", Proc. SPIE 13054, Assurance and Security for AI-enabled Systems, 1305405 (7 June 2024); https://doi.org/10.1117/12.3012765

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