Publication Date
Spring 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Mark Stamp
Second Advisor
Navrati Saxena
Third Advisor
Genya Ishigaki
Keywords
Flipping Attacks, machine learning
Abstract
In this paper we compare traditional machine learning and deep learning models
trained on a malware dataset when subjected to adversarial attack based on label- flipping. Specifically, we investigate the robustness of different models when faced
with varying percentages of misleading labels, assessing their ability to maintain their accuracy in the face of such adversarial manipulations of the training data. This research aims to provide insights into which models are more robust, in the sense of being better able to resist intentional disruptions to the training data. We find that traditional machine learning models and boosting techniques are more robust when subjected to label-flipping attacks, as compared to deep learning models.
Recommended Citation
Bhargava, Sarvagya, "Robustness of Learning Models to Label Flipping Attacks" (2024). Master's Projects. 1402.
https://scholarworks.sjsu.edu/etd_projects/1402
