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...
المؤلفون الرئيسيون: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
التنسيق: | Journal article |
اللغة: | English |
منشور في: |
Journal of Machine Learning Research
2021
|
مواد مشابهة
-
On the hardness of robust classification
حسب: Gourdeau, P, وآخرون
منشور في: (2019) -
When are local queries useful for robust learning?
حسب: Gourdeau, P, وآخرون
منشور في: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
حسب: Gourdeau, P, وآخرون
منشور في: (2022) -
Sample complexity of robust learning against evasion attacks
حسب: Gourdeau, P
منشور في: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
حسب: Blaas, A, وآخرون
منشور في: (2020)