Research

Paper

TESTING March 16, 2026

SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression

Authors

Jingyang Li, Fu Song, Guoqiang Li

Abstract

Deploying Deep Neural Networks (DNNs) on resource-constrained embedded systems requires aggressive model compression techniques like quantization and pruning. However, ensuring that the compressed model preserves the behavioral fidelity of the original design is a critical challenge in the safety-critical system design flow. Existing verification methods often lack scalability or fail to handle the architectural heterogeneity introduced by pruning. In this work, we propose SimCert, a probabilistic certification framework for verifying the behavioral similarity of compressed neural networks. Unlike worst-case analysis, SimCert provides quantitative safety guarantees with adjustable confidence levels. Our framework features: (1) A dual-network symbolic propagation method supporting both quantization and pruning; (2) A variance-aware bounding technique using Bernstein's inequality to tighten safety certificates; and (3) An automated verification toolchain. Experimental results on ACAS Xu and computer vision benchmarks demonstrate that SimCert outperforms state-of-the-art baselines.

Metadata

arXiv ID: 2603.14818
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.14818v1</id>\n    <title>SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression</title>\n    <updated>2026-03-16T04:44:37Z</updated>\n    <link href='https://arxiv.org/abs/2603.14818v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.14818v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Deploying Deep Neural Networks (DNNs) on resource-constrained embedded systems requires aggressive model compression techniques like quantization and pruning. However, ensuring that the compressed model preserves the behavioral fidelity of the original design is a critical challenge in the safety-critical system design flow. Existing verification methods often lack scalability or fail to handle the architectural heterogeneity introduced by pruning. In this work, we propose SimCert, a probabilistic certification framework for verifying the behavioral similarity of compressed neural networks. Unlike worst-case analysis, SimCert provides quantitative safety guarantees with adjustable confidence levels. Our framework features: (1) A dual-network symbolic propagation method supporting both quantization and pruning; (2) A variance-aware bounding technique using Bernstein's inequality to tighten safety certificates; and (3) An automated verification toolchain. Experimental results on ACAS Xu and computer vision benchmarks demonstrate that SimCert outperforms state-of-the-art baselines.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-16T04:44:37Z</published>\n    <arxiv:comment>26 pages, 5 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Jingyang Li</name>\n    </author>\n    <author>\n      <name>Fu Song</name>\n    </author>\n    <author>\n      <name>Guoqiang Li</name>\n    </author>\n  </entry>"
}