Purdue University Graduate School
Browse

ATTACKS ON SAR IMAGE MODELS

Download (22.66 MB)
thesis
posted on 2025-04-10, 20:42 authored by Robert Thomas SegoRobert Thomas Sego

The training and testing of synthetic aperture radar image classifiers and segmentation models, and an investigation into applying electro-optical image model attack techniques to SAR models, such as additive Gaussian noise, splicing, the fast gradient sign method, and adversarial transform networks.

History

Degree Type

  • Master of Science

Department

  • Electrical and Computer Engineering

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Edward J. Delp

Additional Committee Member 2

Mark R. Bell

Additional Committee Member 3

David J. Love