Sample complexity of robust learning against evasion attacks

Thesis

It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. One of the fundamental problems in adversarial machine learning is to quantify how much training data is needed in the presence of so-called evasion attacks, where data is corrupted at test time. In this thesis, we work with the exact-in-the-ball notion of robustness and study the feasibility of adversarially robust learning from the perspective of learning theory, consi...

Expand abstract

Authors: Gourdeau, P

• DOI: 10.5287/ora-nrbzp4zy5
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: adversarial machine learning; evasion attacks; learning theory; robust classification
• Subjects: Computational learning theory