A System for the Detection of Adversarial Attacks in Computer Vision via Performance Metrics

<p>Adversarial attacks, or attacks committed by an adversary to hijack a system, are prevalent in the deep learning tasks of computer vision and are one of the greatest threats to these models' safe and accurate use. These attacks force the trained model to misclassify an image, using pixel-level changes undetectable to the human eye. Various defenses against these attacks exist and are detailed in this work. The work of previous researchers has established that when adversarial attacks occur, different node patterns in a Deep Neural Network (DNN) are activated within the model. Additionally, it is known that CPU and GPU metrics look different when different computations are occurring. This work builds upon that knowledge to hypothesize that the system performance metrics, in the form of CPUs, GPUs, and throughput, will reflect the presence of adversarial input in a DNN. This experiment found that external measurements of system performance metrics did not reflect the presence of adversarial input. This work establishes the beginning stages of using system performance metrics to detect and defend against adversarial attacks. Using performance metrics to defend against adversarial attacks can increase the model's safety, improving the robustness and trustworthiness of DNNs.</p>

Name thesis:degree_name

Master of Science in Electrical & Computer Engineering

Level thesis:degree_level

Thesis - Open Access

Discipline thesis:degree_discipline

Electrical, Computer, Software, and Systems Engineering

Year

2023

Author dc:creator

• Reynolds, Sarah

• adversarial defenses
• DNNs
• CNNs
• neural networks
• adversarial attacks
• system performance metrics
• Artificial Intelligence and Robotics

Repository record dc:identifier

https://commons.erau.edu/edt/776

OAI identifier oai:identifier

oai:commons.erau.edu:edt-1795