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...
主要な著者: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
Journal of Machine Learning Research
2021
|
類似資料
-
On the hardness of robust classification
著者:: Gourdeau, P, 等
出版事項: (2019) -
When are local queries useful for robust learning?
著者:: Gourdeau, P, 等
出版事項: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
著者:: Gourdeau, P, 等
出版事項: (2022) -
Sample complexity of robust learning against evasion attacks
著者:: Gourdeau, P
出版事項: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
著者:: Blaas, A, 等
出版事項: (2020)