Papers › Fixing Data Augmentation to Improve Adversarial Robustness

Fixing Data Augmentation to Improve Adversarial Robustness

2 Mar 2021arXiv:2103.01946archive 2025-07-28

Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

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 ℓ_∞ and ℓ₂ norm-bounded perturbations of size ϵ= 8/255 and ϵ= 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 ℓ_∞ norm-bounded perturbations of size ϵ= 8/255, our model reaches 64.20% robust accuracy without using any external data, beating most prior works that use external data.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

deepmind/deepmind-research officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Disentangling by Subspace Diffusion (arXiv:2006.12982; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified), Characterizing signal propagation to close the performance gap in unnormalized ResNets (arXiv:2101.08692; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
BjoernNieth/LS-Dataset-pruning-in-AT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation (arXiv:2406.13283; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
imrahulr/adversarial_robustness_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Robustness using Generated Data (arXiv:2110.09468; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
imrahulr/hat mentioned on GitHubpytorchSyntology: not harvested report
p2333/score mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robustness and Accuracy Could Be Reconcilable by (Proper) Definition (arXiv:2202.10103; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
wzekai99/dm-improves-at mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A combination of noise and bilateral filters achieve supralinear and scalable... (arXiv:2606.02267; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
yuyuwu5/ADR mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Annealing Self-Distillation Rectification Improves Adversarial Training (arXiv:2305.12118; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial RobustnessData Augmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections