Back to results

University of South Florida

Exploring the Vulnerability of A Neural Tangent Generalization Attack (NTGA) - Generated Unlearnable CIFAR-10 Dataset

Abstract

dc:description

Nowadays, a massive amount of data is generated and stored on servers and cloudsfrom various applications daily. Preventing these data from unauthorized use often becomes necessary and critical in various real-world applications. Many researchers have studied this crucial problem and developed different methods for this purpose. Among them, Neural Tangent Generalization Attack (NTGA) is one of the most efficient methods to make a dataset unlearnable, which means that the dataset is not learnable by machine learning/deep learning methods. That is, the NTGA-generated dataset is protected against unauthorized use. In this thesis, we explore the vulnerability of an NTGA-generated unlearnable CIFAR-10 dataset. Specifically, we show that by employing data augmentation, we can still train a model using the CIFAR-10 dataset generated by NTGA in a centralized learning environment. That is, we experimentally prove that the NTGA-generated unlearnable CIFAR-10 dataset is vulnerable or learnable. To reduce the execution time of learning from the dataset, we further study the vulnerability of the unlearnable dataset in a decentralized learning (i.e., federated learning) environment. Our experiments demonstrate the efficiency of the proposed decentralized method. After all, we reduce the execution time for learning from the unlearnable dataset when using decentralized learning compared to centralized learning.

Degree

thesis:*
Name thesis:degree_name
Master of Arts (M.A.)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Mathematics and Statistics
Grantor
University of South Florida
Year dc:date
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ost, Gitte
Contributors dc:contributor
  • Kaiqi Xiong, Ph.D.
  • Lu Lu, Ph.D.
  • Razvan Teodorescu, Ph.D.
  • Jiwoong Kim, Ph.D.

Subjects

dc:subject × 6

Identifiers

dc:identifier.*
Repository record dc:identifier
https://digitalcommons.usf.edu/etd/10399

Chain of custody

source
Harvested from
University of South Florida
Base URL
digitalcommons.usf.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ost, Gitte. Exploring the Vulnerability of A Neural Tangent Generalization Attack (NTGA) - Generated Unlearnable CIFAR-10 Dataset. Thesis thesis, University of South Florida, 2022. https://digitalcommons.usf.edu/etd/10399