Adversarial Examples in Simpler Settings
In this thesis we explore adversarial examples for simple model families and simple data distributions, focusing in particular on linear and kernel classifiers. On the theoretical front we find evidence that natural accuracy and robust accuracy are more likely than not to be misaligned. We conclude...
| Autore principale: | |
|---|---|
| Altri autori: | |
| Natura: | Tesi |
| Pubblicazione: |
Massachusetts Institute of Technology
2022
|
| Accesso online: | https://hdl.handle.net/1721.1/139041 |