Pith. sign in

REVIEW 5 cited by

Fixing Data Augmentation to Improve Adversarial Robustness

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.01946 v2 pith:J6T5W2CH submitted 2021-03-02 cs.CV cs.LG

Sylvestre-Alvise Rebuffi , Sven Gowal , Dan A. Calian , Florian Stimberg , Olivia Wiles , Timothy Mann This is my paper · ORCID
classification cs.CVcs.LG
keywords robustaccuracydataadversarialepsilonsizetrainingaugmentation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

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 $\ell_\infty$ and $\ell_2$ norm-bounded perturbations of size $\epsilon = 8/255$ and $\epsilon = 128/255$, 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 $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our model reaches 64.20% robust accuracy without using any external data, beating most prior works that use external data.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Adversarial Training from Mean Field Perspective

    cs.LG 2025-05 reject novelty 7.0 of 10

    A mean field framework for random ReLU networks yields adversarial-loss bounds and predicts that adversarial training shrinks weights, hurts vanilla depth, and is rescued by residual connections and width.

  2. AMRM-Pure: Semantic-Preserving Adversarial Purification

    cs.CR 2026-07 conditional novelty 6.5 of 10

    AMRM-Pure purifies adversarial images by minimizing reconstruction loss of attentive mask models (MAE/MaskDiT) to restore patch-level semantic relations, with optional classifier fine-tuning for SOTA robust accuracy.

  3. Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A greedy, query-budgeted attack-ensemble framework approximates the minimum-perturbation frontier and yields an ε-free defense ranking (DOI).

  4. Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method

    cs.CV 2026-03 conditional novelty 5.0 of 10

    A progressive curriculum that trains open-vocabulary detectors on low-ambiguity, high-signal cross-modal alignments first improves robustness to visual domain shifts, with modest, test-tuned gains.

  5. RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function

    cs.LG 2025-07 reject novelty 2.0 of 10

    RCR-AF, a clipped scaled-softplus activation, is claimed to improve CIFAR-10 accuracy and robustness, but the evidence is undermined by test-set tuning and a flawed complexity derivation.

Pith tools