Research

Paper

TESTING March 19, 2026

Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection

Authors

Ján Mikulec, Jakub Breier, Xiaolu Hou

Abstract

Test Vector Leakage Assessment (TVLA) based on Welch's $t$-test has become a standard tool for detecting side-channel leakage. However, its mean-based nature can limit sensitivity when leakage manifests primarily through higher-order distributional differences. As our experiments show, this property becomes especially crucial when it comes to evaluating neural network implementations. In this work, we propose Anderson--Darling Leakage Assessment (ADLA), a leakage detection framework that applies the two-sample Anderson--Darling test for leakage detection. Unlike TVLA, ADLA tests equality of the full cumulative distribution functions and does not rely on a purely mean-shift model. We evaluate ADLA on a multilayer perceptron (MLP) trained on MNIST and implemented on a ChipWhisperer-Husky evaluation platform. We consider protected implementations employing shuffling and random jitter countermeasures. Our results show that ADLA can provide improved leakage-detection sensitivity in protected implementations for a low number of traces compared to TVLA.

Metadata

arXiv ID: 2603.18647
Provider: ARXIV
Primary Category: cs.CR
Published: 2026-03-19
Fetched: 2026-03-20 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.18647v1</id>\n    <title>Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection</title>\n    <updated>2026-03-19T09:12:04Z</updated>\n    <link href='https://arxiv.org/abs/2603.18647v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.18647v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Test Vector Leakage Assessment (TVLA) based on Welch's $t$-test has become a standard tool for detecting side-channel leakage. However, its mean-based nature can limit sensitivity when leakage manifests primarily through higher-order distributional differences. As our experiments show, this property becomes especially crucial when it comes to evaluating neural network implementations. In this work, we propose Anderson--Darling Leakage Assessment (ADLA), a leakage detection framework that applies the two-sample Anderson--Darling test for leakage detection. Unlike TVLA, ADLA tests equality of the full cumulative distribution functions and does not rely on a purely mean-shift model.\n  We evaluate ADLA on a multilayer perceptron (MLP) trained on MNIST and implemented on a ChipWhisperer-Husky evaluation platform. We consider protected implementations employing shuffling and random jitter countermeasures. Our results show that ADLA can provide improved leakage-detection sensitivity in protected implementations for a low number of traces compared to TVLA.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-19T09:12:04Z</published>\n    <arxiv:primary_category term='cs.CR'/>\n    <author>\n      <name>Ján Mikulec</name>\n    </author>\n    <author>\n      <name>Jakub Breier</name>\n    </author>\n    <author>\n      <name>Xiaolu Hou</name>\n    </author>\n  </entry>"
}