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...
Auteurs principaux: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
Format: | Journal article |
Langue: | English |
Publié: |
Journal of Machine Learning Research
2021
|
Documents similaires
-
On the hardness of robust classification
par: Gourdeau, P, et autres
Publié: (2019) -
When are local queries useful for robust learning?
par: Gourdeau, P, et autres
Publié: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
par: Gourdeau, P, et autres
Publié: (2022) -
Sample complexity of robust learning against evasion attacks
par: Gourdeau, P
Publié: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
par: Blaas, A, et autres
Publié: (2020)