Adversarially robust machine learning with guarantees
Abstract/Contents
- Abstract
- Machine learning (ML) systems are remarkably successful on a variety of benchmarks across several domains. In these benchmarks, the test data points, though not identical, are very similar to the training data. On the other hand, success in the real world requires good performance across a broad range of inputs that are potentially very different from the training data. Self-driving cars encounter unexpected construction zones, predictive health-care systems run into unforeseen changes in demographics, and real world systems are exposed to attackers who strategically generate inputs. Unfortunately, current ML systems are brittle and fail even under extremely small changes to inputs, as demonstrated by the existence of adversarial examples. As ML systems are becoming widely deployed, we need to build robust ML models that are guaranteed to work well across a wide range of inputs. While adversarial examples attracted widespread attention, progress has been limited by critical computational and statistical roadblocks which we address in this thesis.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2021; ©2021 |
Publication date | 2021; 2021 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Raghunathan, Aditi |
---|---|
Degree supervisor | Liang, Percy |
Thesis advisor | Liang, Percy |
Thesis advisor | Hashimoto, Tatsunori |
Thesis advisor | Ma, Tengyu |
Degree committee member | Hashimoto, Tatsunori |
Degree committee member | Ma, Tengyu |
Associated with | Stanford University, Computer Science Department |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Aditi Raghunathan. |
---|---|
Note | Submitted to the Computer Science Department. |
Thesis | Thesis Ph.D. Stanford University 2021. |
Location | https://purl.stanford.edu/sw855vz6069 |
Access conditions
- Copyright
- © 2021 by Aditi Raghunathan
Also listed in
Loading usage metrics...