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