University of Illinois Urbana-Champaign

Improving robust accuracy through gradient boosting with ADP

Fan, Zhicong

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/110269

Description

Title
Improving robust accuracy through gradient boosting with ADP
Author(s)
Fan, Zhicong
Contributor(s)
Li, Bo
Issue Date
2021-05
Keyword(s)
  • Adversarial Machine Learning
  • Gradient Boosting
  • Ensemble Model
  • Adaptive Diversity Promoting Strategy
  • XGBoost
  • Deep Neural Networks
Abstract
In adversarial examples, humans can easily classify the images even though the images are corrupted. However, recently, some related work has shown that deep neural networks are vulnerable to adversarial attacks [1]. To increase the robustness against adversarial attacks, many methods were carried out, such as k-Winners [2], robust sparse Fourier Transform [3], and Compact Convolution [4]. Many of the defense strategies aimed to mark the gradient, train different classifiers, and use new loss calculations. In the thesis, several ensemble models were trained by applying both typical gradient boosting and enlarging the diversity among base models to improve their robustness against adversarial attacks. The purpose is to show that making adversarial examples difficult to transfer among individual members would cause the state-of-the-art attacking algorithms to fail to attack the trained robust ensemble model to a certain extent.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/110269

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research