CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 13054 > Article
Presentation + Paper
7 June 2024 Bayesian graph representation learning for adversarial patch detection
Alexander M. Berenbeim, Alexander V. Wei, Adam Cobb, Anirban Roy, Susmit Jha, Nathaniel D. Bastian
Author Affiliations +
Proceedings Volume 13054, Assurance and Security for AI-enabled Systems; 1305409 (2024) https://doi.org/10.1117/12.3013128
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States
Abstract
Representing context, reasoning within contexts, and providing quantitative assessments of machine learning (ML) model certainty are all tasks of fundamental importance for secure, interpretable, and reliable model development. Recent enthusiasm regarding generative ML models has highlighted the importance of representing context, which is contingent on relevant and contextual features of data and model predictions are unreliable on out-of-context inputs. Herein, we develop the theory of graph representation learning (GRL) to extend to Bayesian Graph Neural Networks and to incorporate various forms of uncertainty quantification to improve model development and application in the presence of adversarial attacks. Within this framework, we approach the challenge of adversarial patch detection using a synthesized dataset consisting of images from the APRICOT and COCO datasets to study various binary classification models for patch detection. We present GRL models with two layers of edge convolution that are capable of detecting patches with up to 93.5% accuracy. Further, we find evidence supporting the use of the certainty and competence framework for model predictions as a tool for detecting patches, particularly when the former is included as a model feature in graph neural networks.
Conference Presentation
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Alexander M. Berenbeim, Alexander V. Wei, Adam Cobb, Anirban Roy, Susmit Jha, and Nathaniel D. Bastian "Bayesian graph representation learning for adversarial patch detection", Proc. SPIE 13054, Assurance and Security for AI-enabled Systems, 1305409 (7 June 2024); https://doi.org/10.1117/12.3013128
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
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
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 17 PAGES + PRESENTATION
DOWNLOAD PAPER SAVE TO MY LIBRARY
WATCH
PRESENTATION
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection
Data modeling
Neural networks
Machine learning
Convolution
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top