Research

Paper

TESTING March 03, 2026

IoUCert: Robustness Verification for Anchor-based Object Detectors

Authors

Benedikt Brückner, Alejandro Mercado, Yanghao Zhang, Panagiotis Kouvaros, Alessio Lomuscio

Abstract

While formal robustness verification has seen significant success in image classification, scaling these guarantees to object detection remains notoriously difficult due to complex non-linear coordinate transformations and Intersection-over-Union (IoU) metrics. We introduce {\sc \sf IoUCert}, a novel formal verification framework designed specifically to overcome these bottlenecks in foundational anchor-based object detection architectures. Focusing on the object localisation component in single-object settings, we propose a coordinate transformation that enables our algorithm to circumvent precision-degrading relaxations of non-linear box prediction functions. This allows us to optimise bounds directly with respect to the anchor box offsets which enables a novel Interval Bound Propagation method that derives optimal IoU bounds. We demonstrate that our method enables, for the first time, the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.

Metadata

arXiv ID: 2603.03043
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03043v1</id>\n    <title>IoUCert: Robustness Verification for Anchor-based Object Detectors</title>\n    <updated>2026-03-03T14:36:46Z</updated>\n    <link href='https://arxiv.org/abs/2603.03043v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03043v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>While formal robustness verification has seen significant success in image classification, scaling these guarantees to object detection remains notoriously difficult due to complex non-linear coordinate transformations and Intersection-over-Union (IoU) metrics. We introduce {\\sc \\sf IoUCert}, a novel formal verification framework designed specifically to overcome these bottlenecks in foundational anchor-based object detection architectures. Focusing on the object localisation component in single-object settings, we propose a coordinate transformation that enables our algorithm to circumvent precision-degrading relaxations of non-linear box prediction functions. This allows us to optimise bounds directly with respect to the anchor box offsets which enables a novel Interval Bound Propagation method that derives optimal IoU bounds. We demonstrate that our method enables, for the first time, the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-03T14:36:46Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Benedikt Brückner</name>\n    </author>\n    <author>\n      <name>Alejandro Mercado</name>\n    </author>\n    <author>\n      <name>Yanghao Zhang</name>\n    </author>\n    <author>\n      <name>Panagiotis Kouvaros</name>\n    </author>\n    <author>\n      <name>Alessio Lomuscio</name>\n    </author>\n  </entry>"
}