Back to search

Central Florida

Adversarial Attacks On Vision Algorithms Using Deep Learning Features

Abstract

dc:description.abstract

Computer vision algorithms, such as those implementing object detection, are known to be susceptible to adversarial attacks. Small barely perceptible perturbations to the input can cause vision algorithms to incorrectly classify inputs that they would have otherwise classified correctly. A number of approaches have been recently investigated to generate such adversarial examples for deep neural networks. Many of these approaches either require grey-box access to the deep neural net being attacked or rely on adversarial transfer and grey-box access to a surrogate neural network. In this thesis, we present an approach to the synthesis of adversarial examples for computer vision algorithms that only requires black-box access to the algorithm being attacked. Our attack approach employs fuzzing with features derived from the layers of a convolutional neural network trained on adversarial examples from an unrelated dataset. Based on our experimental results, we believe that our validation approach will enable designers of cyber-physical systems and other high-assurance use-cases of vision algorithms to stress test their implementations.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Michel, Andy
Contributors dc:contributor
  • Jha, Sumit Kumar

Subjects

dc:subject × 1

Rights

Language dc:language
English

Identifiers

dc:identifier.*
Identifier
CFE0006898

Chain of custody

source
Harvested from
Central Florida
Base URL
stars.library.ucf.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Michel, Andy. Adversarial Attacks On Vision Algorithms Using Deep Learning Features. https://stars.library.ucf.edu/etd/5675