Research

Paper

TESTING March 25, 2026

Walma: Learning to See Memory Corruption in WebAssembly

Authors

Oussama Draissi, Mark Günzel, Ahmad-Reza Sadeghi, Lucas Davi

Abstract

WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go undetected when a malicious host tampers with a module's state. Existing defenses rely on invasive binary instrumentation or custom runtimes, and do not address runtime integrity verification under an adversarial host model. We present Walma, a framework for WebAssembly Linear Memory Attestation that leverages machine learning to detect memory corruption and external tampering by classifying memory snapshots. We evaluate Walma on six real-world CVE-affected applications across three verification backends (cpu-wasm, cpu-tch, gpu) and three instrumentation policies. Our results demonstrate that CNN-based classification can effectively detect memory corruption in applications with structured memory layouts, with coarse-grained boundary checks incurring as low as 1.07x overhead, while fine-grained monitoring introduces higher (1.5x--1.8x) but predictable costs. Our evaluation quantifies the accuracy and overhead trade-offs across deployment configurations, demonstrating the practical feasibility of ML-based memory attestation for WebAssembly.

Metadata

arXiv ID: 2603.24167
Provider: ARXIV
Primary Category: cs.CR
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24167v1</id>\n    <title>Walma: Learning to See Memory Corruption in WebAssembly</title>\n    <updated>2026-03-25T10:34:29Z</updated>\n    <link href='https://arxiv.org/abs/2603.24167v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24167v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go undetected when a malicious host tampers with a module's state. Existing defenses rely on invasive binary instrumentation or custom runtimes, and do not address runtime integrity verification under an adversarial host model. We present Walma, a framework for WebAssembly Linear Memory Attestation that leverages machine learning to detect memory corruption and external tampering by classifying memory snapshots. We evaluate Walma on six real-world CVE-affected applications across three verification backends (cpu-wasm, cpu-tch, gpu) and three instrumentation policies. Our results demonstrate that CNN-based classification can effectively detect memory corruption in applications with structured memory layouts, with coarse-grained boundary checks incurring as low as 1.07x overhead, while fine-grained monitoring introduces higher (1.5x--1.8x) but predictable costs. Our evaluation quantifies the accuracy and overhead trade-offs across deployment configurations, demonstrating the practical feasibility of ML-based memory attestation for WebAssembly.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-25T10:34:29Z</published>\n    <arxiv:comment>9 pages, 4 figures, 3 tables</arxiv:comment>\n    <arxiv:primary_category term='cs.CR'/>\n    <author>\n      <name>Oussama Draissi</name>\n    </author>\n    <author>\n      <name>Mark Günzel</name>\n    </author>\n    <author>\n      <name>Ahmad-Reza Sadeghi</name>\n    </author>\n    <author>\n      <name>Lucas Davi</name>\n    </author>\n  </entry>"
}