The Role of Feature Vector Scale in the Adversarial Vulnerability of Convolutional Neural Networks
Year: 2025
Type: article
Abstract: In image classification, convolutional neural networks (CNNs) remain vulnerable to visually imperceptible perturbations, often called adversarial examples. Although various hypotheses have been proposed to explain this vulnerability, a clear cause has not been established. We hypothesize an unfair learning effect: samples are learned unevenly depending on the scale (norm) of their feature vectors in feature space. As a result, feature vectors with different scales exhibit different levels of robustness against noise. To test this hypothesis, we conduct vulnerability tests on CIFAR-10 using a standard convolutional classifier, analyzing cosine similarity between original and perturbed feature vectors, as well as error rates across scale intervals. Our experiments show that small-scale feature vectors are highly vulnerable. This is reflected in low cosine similarity and high error rates, whereas large-scale feature vectors consistently exhibit greater robustness with high cosine similarity and low error rates. These findings highlight the critical role of feature vector scale in adversarial vulnerability.
Source: Mathematics
DOI: 10.3390/math13183026
Authors: Hyun-Cheol Park, Sang-Woong Lee
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,137
OpenAlex ID: W4414355236