Pith. sign in

REVIEW 1 cited by

AdvRush: Searching for Adversarially Robust Neural Architectures

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 2108.01289 v2 pith:JVGZLDNP submitted 2021-08-03 cs.LG cs.AI

classification cs.LGcs.AI
keywords neuralrobustadvrushtrainingadversarialarchitectureadversariallyrobustness
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep neural networks continue to awe the world with their remarkable performance. Their predictions, however, are prone to be corrupted by adversarial examples that are imperceptible to humans. Current efforts to improve the robustness of neural networks against adversarial examples are focused on developing robust training methods, which update the weights of a neural network in a more robust direction. In this work, we take a step beyond training of the weight parameters and consider the problem of designing an adversarially robust neural architecture with high intrinsic robustness. We propose AdvRush, a novel adversarial robustness-aware neural architecture search algorithm, based upon a finding that independent of the training method, the intrinsic robustness of a neural network can be represented with the smoothness of its input loss landscape. Through a regularizer that favors a candidate architecture with a smoother input loss landscape, AdvRush successfully discovers an adversarially robust neural architecture. Along with a comprehensive theoretical motivation for AdvRush, we conduct an extensive amount of experiments to demonstrate the efficacy of AdvRush on various benchmark datasets. Notably, on CIFAR-10, AdvRush achieves 55.91% robust accuracy under FGSM attack after standard training and 50.04% robust accuracy under AutoAttack after 7-step PGD adversarial training.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. SEAL: Searching Expandable Architectures for Incremental Learning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    SEAL jointly searches a neural network architecture and an expansion policy, expanding the network only when a capacity threshold is exceeded, and reports competitive accuracy with lower average forgetting on CIFAR-10...

Pith tools