The Impact of Scaling Training Data on Adversarial Robustness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zimmerli, Marco, Plesner, Andreas, Aczel, Till, Wattenhofer, Roger
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915524631330816
author Zimmerli, Marco
Plesner, Andreas
Aczel, Till
Wattenhofer, Roger
author_facet Zimmerli, Marco
Plesner, Andreas
Aczel, Till
Wattenhofer, Roger
contents Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-the-art vision models spanning supervised, self-supervised, and contrastive learning approaches, trained on datasets from 1.2M to 22B images. Models were evaluated under six black-box attack categories: random perturbations, two types of geometric masks, COCO object manipulations, ImageNet-C corruptions, and ImageNet-R style shifts. Robustness follows a logarithmic scaling law with both data volume and model size: a tenfold increase in data reduces attack success rate (ASR) on average by ~3.2%, whereas a tenfold increase in model size reduces ASR on average by ~13.4%. Notably, some self-supervised models trained on curated datasets, such as DINOv2, outperform others trained on much larger but less curated datasets, challenging the assumption that scale alone drives robustness. Adversarial fine-tuning of ResNet50s improves generalization across structural variations but not across color distributions. Human evaluation reveals persistent gaps between human and machine vision. These results show that while scaling improves robustness, data quality, architecture, and training objectives play a more decisive role than raw scale in achieving broad-spectrum adversarial resilience.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Impact of Scaling Training Data on Adversarial Robustness
Zimmerli, Marco
Plesner, Andreas
Aczel, Till
Wattenhofer, Roger
Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
Machine Learning
Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-the-art vision models spanning supervised, self-supervised, and contrastive learning approaches, trained on datasets from 1.2M to 22B images. Models were evaluated under six black-box attack categories: random perturbations, two types of geometric masks, COCO object manipulations, ImageNet-C corruptions, and ImageNet-R style shifts. Robustness follows a logarithmic scaling law with both data volume and model size: a tenfold increase in data reduces attack success rate (ASR) on average by ~3.2%, whereas a tenfold increase in model size reduces ASR on average by ~13.4%. Notably, some self-supervised models trained on curated datasets, such as DINOv2, outperform others trained on much larger but less curated datasets, challenging the assumption that scale alone drives robustness. Adversarial fine-tuning of ResNet50s improves generalization across structural variations but not across color distributions. Human evaluation reveals persistent gaps between human and machine vision. These results show that while scaling improves robustness, data quality, architecture, and training objectives play a more decisive role than raw scale in achieving broad-spectrum adversarial resilience.
title The Impact of Scaling Training Data on Adversarial Robustness
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2509.25927