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...
Những tác giả chính: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
Định dạng: | Journal article |
Ngôn ngữ: | English |
Được phát hành: |
Journal of Machine Learning Research
2021
|
Những quyển sách tương tự
-
On the hardness of robust classification
Bằng: Gourdeau, P, et al.
Được phát hành: (2019) -
When are local queries useful for robust learning?
Bằng: Gourdeau, P, et al.
Được phát hành: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
Bằng: Gourdeau, P, et al.
Được phát hành: (2022) -
Sample complexity of robust learning against evasion attacks
Bằng: Gourdeau, P
Được phát hành: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
Bằng: Blaas, A, et al.
Được phát hành: (2020)