Back to search

Michigan State University

Robust learning of deep neural networks under data corruption

Abstract

dc:description

Training deep neural networks in the presence of corrupted data is challenging as the corrupted data points may significantly impact generalization performance of the models. Unfortunately, the data corruption issue widely exists in many application domains, including but not limited to, healthcare, environmental sciences, autonomous driving, and social media analytics. Although there have been some previous studies that aim to enhance the robustness of machine learning models against data corruption, most of them either lack theoretical robustness guarantees or unable to scale to the millions of model parameters governing deep neural networks. The goal of this thesis is to design robust machine learning algorithms that 1) effectively deal with different types of data corruption, 2) have sound theoretical guarantees on robustness, and 3) scalable to large number of parameters in deep neural networks.There are two general approaches to enhance model robustness against data corruption. The first approach is to detect and remove the corrupted data while the second approach is to design robust learning algorithms that can tolerate some fraction of corrupted data. In this thesis, I had developed two robust unsupervised anomaly detection algorithms and two robust supervised learning algorithm for corrupted supervision and backdoor attack. Specifically, in Chapter 2, I proposed the Robust Collaborative Autoencoder (RCA) approach to enhance the robustness of vanilla autoencoder methods against natural corruption. In Chapter 3, I developed Robust RealNVP, a robust density estimation technique for unsupervised anomaly detection tasks given concentrated anomalies. Chapter 4 presents the Provable Robust Learning (PRL) approach, which is a robust algorithm against agnostic corrupted supervision. In Chapter 5, a meta-algorithm to defend against backdoor attacks is proposed by exploring the connection between label corruption and backdoor data poisoning attack. Extensive experiments on multiple benchmark datasets have demonstrated the robustness of the proposed algorithms under different types of corruption.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Liu, Boyang
Contributors dc:contributor
  • Tan, Pang-Ning PT
  • Zhou, Jiayu JZ
  • Tang, Jiliang JT
  • Cheruvelil, Kendra KC

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • In Copyright
Language dc:language
English

Identifiers

dc:identifier.*
Identifier
etd:50530
isbn:9798834063872
oclc:on1373601430
oclc:1373601430
umi:29253314
local:Liu_grad.msu_0128D_19164

Chain of custody

source
Harvested from
Michigan State University
Base URL
d.lib.msu.edu/oai
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Liu, Boyang. Robust learning of deep neural networks under data corruption. 2022. https://doi.org/doi:10.25335/ywk2-8j42