[2603.03043] IoUCert: Robustness Verification for Anchor-based Object Detectors

Computer Science > Machine Learning arXiv:2603.03043 (cs) [Submitted on 3 Mar 2026] Title:IoUCert: Robustness Verification for Anchor-based Object Detectors Authors:Benedikt Brückner, Alejandro Mercado, Yanghao Zhang, Panagiotis Kouvaros, Alessio Lomuscio View a PDF of the paper titled IoUCert: Robustness Verification for Anchor-based Object Detectors, by Benedikt Br\"uckner and 4 other authors View PDF 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. Subjects: Machine Learning (cs.LG); Ar...