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...
Hauptverfasser: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
Format: | Journal article |
Sprache: | English |
Veröffentlicht: |
Journal of Machine Learning Research
2021
|
Ähnliche Einträge
Ähnliche Einträge
-
On the hardness of robust classification
von: Gourdeau, P, et al.
Veröffentlicht: (2019) -
When are local queries useful for robust learning?
von: Gourdeau, P, et al.
Veröffentlicht: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
von: Gourdeau, P, et al.
Veröffentlicht: (2022) -
Sample complexity of robust learning against evasion attacks
von: Gourdeau, P
Veröffentlicht: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
von: Blaas, A, et al.
Veröffentlicht: (2020)