Sylvestre-Alvise Rebuffi, Timothy Mann, Sven Gowal, Dan Calian, Florian Stimberg, Olivia Wiles
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce robust overfitting. First, we demonstrate that, contrary to previous findings, when combined with model weight averaging, data augmentation can significantly boost robust accuracy. Second, we explore how state-of-the-art generative models can be leveraged to artificially increase the size of the training set and further improve adversarial robustness. Finally, we evaluate our approach on CIFAR-10 against ∞ and 2 norm-bounded perturbations of size = 8/255 and = 128/255, respectively. We show large absolute improvements of +7.06% and +5.88% in robust accuracy compared to previous state-of-the-art methods. In particular, against ∞ norm-bounded perturbations of size = 8/255, our model reaches 64.20% robust accuracy without using any external data, beating most prior works that use external data. Since its original publication (2 Mar 2021), this paper has been accepted to NeurIPS 2021 as two separate and updated papers (Rebuffi et al., 2021;Gowal et al., 2021). The new papers improve results and clarity.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.01946")
get_code_for_paper("2103.01946")
have("2103.01946")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.01946.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.01946)
Connect an agent — have() is free.