Pith. sign in

REVIEW 2 cited by

Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training

Not yet reviewed by Pith; the record is open.

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 2006.00387 v1 pith:IGJX3OHR submitted 2020-05-30 cs.LG stat.ML

classification cs.LGstat.ML
keywords networksadversarialrobustnesstrainingadaptiveobjectivenon-adaptiveoutperform
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it is common practice to train on widened networks with more parameters. To boost robustness, we propose a conditional normalization module to adapt networks when conditioned on input samples. Our adaptive networks, once adversarially trained, can outperform their non-adaptive counterparts on both clean validation accuracy and robustness. Our method is objective agnostic and consistently improves both the conventional adversarial training objective and the TRADES objective. Our adaptive networks also outperform larger widened non-adaptive architectures that have 1.5 times more parameters. We further introduce several practical ``tricks'' in adversarial training to improve robustness and empirically verify their efficiency.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Improving Adversarial Robustness Through Adaptive Learning-Driven Multi-Teacher Knowledge Distillation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A multi-teacher adversarial robustness distillation method (MTKD-AR) trains a clean-data student using cosine-similarity-weighted logits from adversarially trained teachers, reporting improved robustness on MNIST and ...

  2. Copula Analysis of Risk: A Multivariate Risk Analysis for VaR and CoVaR using Copulas and DCC-GARCH

    q-fin.RM 2025-05 reject novelty 2.0 of 10

    A course-project comparison of Gaussian, Student-t, Clayton, and Gumbel copulas within a DCC-GARCH pipeline, reporting in-sample goodness-of-fit and VaR/CoVaR estimates for six stocks.

Pith tools