Abstract
dc:description.abstractMachine learning methods have become a commodity in the toolkits of both researchers and practitioners. For performance and privacy reasons, new applications often rely on third-party code or pretrained models, train on crowd-sourced data, and sometimes move learning to users’ devices. This introduces vulnerabilities such as backdoors, i.e., unrelated tasks that the model may unintentionally learn when an adversary controls parts of the training data or pipeline. In this thesis, we identify new threats to ML models and propose approaches that balance security, accuracy, and privacy without disruptive changes to the existing training infrastructures.
Degree
thesis:*- Name thesis:degree_name
- Ph. D., Computer Science
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Computer Science
- Grantor
- Cornell University
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bagdasaryan, Eugene
- Chair dc:contributor.chair
-
- Shmatikov, Vitaly
- Committee members dc:contributor.committeemember
-
- Estrin, Deborah
- Belongie, Serge
- Lee, Clarence
Subjects
dc:subject × 2Rights
dc:rights- Statement dc:rights
-
- Attribution 4.0 International
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 16219353
- Dc Identifier Other
-
ProQuest Submission ID: 13889
ProQuest Publication ID: 30575621