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...
Κύριοι συγγραφείς: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
Μορφή: | Journal article |
Γλώσσα: | English |
Έκδοση: |
Journal of Machine Learning Research
2021
|
Παρόμοια τεκμήρια
Παρόμοια τεκμήρια
-
On the hardness of robust classification
ανά: Gourdeau, P, κ.ά.
Έκδοση: (2019) -
When are local queries useful for robust learning?
ανά: Gourdeau, P, κ.ά.
Έκδοση: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
ανά: Gourdeau, P, κ.ά.
Έκδοση: (2022) -
Sample complexity of robust learning against evasion attacks
ανά: Gourdeau, P
Έκδοση: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
ανά: Blaas, A, κ.ά.
Έκδοση: (2020)