Generalized No Free Lunch Theorem for Adversarial Robustness

By Elvis Dohmatob. 2018

82 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Certified Adversarial Robustness via Randomized Smoothing (2019, background): “Recent theoretical work has taken steps towards addressing this question (Mahloujifar et al., 2019; Gilmer et al., 2018b; Fawzi et al., 2018; Tsipras et al., 2019; Schmidt et al., 2018; Shafahi et al., 2019; Dohma- tob, 2018; Bubeck et al., 2018b).”
Adversarial Examples Are a Natural Consequence of Test Error in Noise (2019, background): “There is an existing research program (Gilmer et al., 2018b; Mahloujifar et al., 2018; Dohmatob, 2018) which proves hard upper bounds on adversarial robustness in terms of the error rate of a model.”
The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization (2020, background): “Theoretically, Dohmatob [2019] showed that a classifier with high standard accuracy can inevitably be fooled by a strong adversary. Empirically, Papernot et al. [2016] and Tsipras et al. [2019] found that a strong adversary can drive down standard accuracy for robust models.”
A Closer Look at Accuracy vs. Robustness (2020, background): “In other words, we have further evidence that well-curated benchmark datasets are insufficient to demonstrate a tradeoff between robustness and accuracy, in contrast to predictions of an inevitable tradeoff [11, 12, 16, 57].”
Learning From Noisy Labels With Deep Neural Networks: A Survey (2020, background): “There has been a lot of research on the robustness of deep learning under input perturbation, mainly in the ﬁeld of adversarial training where the input feature is maliciously perturbed to distort the output of the DNN [34], [36].”