Paper
12 April 2021 What’s data got to do with it?
Jamie Godwin, Donald Waagen, Donald Hulsey, Ryland Lyons, Rachel Mattson, Jacob Garcia, Duane Geci, Railey Conner
Author Affiliations +
Abstract
Continued advancements in adversarial attacks have crippled neural network performance. These small pixel perturbations can go undetected and cause networks to misclassify with high confidence. The motivation for this paper was to investigate how various sensor modalities and network models respond to adversarial attacks. It is important to realize that the large diversity in neural network architectures makes it difficult for any analytical conclusions to be made that generalize across any given neural network. For this reason, we share the statistical analyses performed which could be applied to any network under review. General observations gained from this analysis are also shared which indicated that network classification accuracy is not just a function of the network model but the data as well.
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jamie Godwin, Donald Waagen, Donald Hulsey, Ryland Lyons, Rachel Mattson, Jacob Garcia, Duane Geci, and Railey Conner "What’s data got to do with it?", Proc. SPIE 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, 117460Q (12 April 2021); https://doi.org/10.1117/12.2587479
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Statistical analysis

Distance measurement

Neural networks

Analytical research

Network architectures

Back to Top