On the hardness of robust classification
It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. In this paper we study the feasibility of adversarially robust learning from the perspective of computational learning theory, considering both sample and computational complexity...
Үндсэн зохиолчид: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
Формат: | Journal article |
Хэл сонгох: | English |
Хэвлэсэн: |
Journal of Machine Learning Research
2021
|
Ижил төстэй зүйлс
-
On the hardness of robust classification
-н: Gourdeau, P, зэрэг
Хэвлэсэн: (2019) -
When are local queries useful for robust learning?
-н: Gourdeau, P, зэрэг
Хэвлэсэн: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
-н: Gourdeau, P, зэрэг
Хэвлэсэн: (2022) -
Sample complexity of robust learning against evasion attacks
-н: Gourdeau, P
Хэвлэсэн: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
-н: Blaas, A, зэрэг
Хэвлэсэн: (2020)