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...
Asıl Yazarlar: | Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J |
---|---|
Materyal Türü: | Journal article |
Dil: | English |
Baskı/Yayın Bilgisi: |
Journal of Machine Learning Research
2021
|
Benzer Materyaller
-
On the hardness of robust classification
Yazar:: Gourdeau, P, ve diğerleri
Baskı/Yayın Bilgisi: (2019) -
When are local queries useful for robust learning?
Yazar:: Gourdeau, P, ve diğerleri
Baskı/Yayın Bilgisi: (2023) -
Sample complexity bounds for robustly learning decision lists against evasion attacks
Yazar:: Gourdeau, P, ve diğerleri
Baskı/Yayın Bilgisi: (2022) -
Sample complexity of robust learning against evasion attacks
Yazar:: Gourdeau, P
Baskı/Yayın Bilgisi: (2023) -
Adversarial robustness guarantees for classification with Gaussian Processes
Yazar:: Blaas, A, ve diğerleri
Baskı/Yayın Bilgisi: (2020)