IoUCert: Robustness Verification for Anchor-based Object Detectors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914369488551936 |
|---|---|
| author | Brückner, Benedikt Mercado, Alejandro J. Zhang, Yanghao Kouvaros, Panagiotis Lomuscio, Alessio |
| author_facet | Brückner, Benedikt Mercado, Alejandro J. Zhang, Yanghao Kouvaros, Panagiotis Lomuscio, Alessio |
| contents | 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 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03043 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IoUCert: Robustness Verification for Anchor-based Object Detectors Brückner, Benedikt Mercado, Alejandro J. Zhang, Yanghao Kouvaros, Panagiotis Lomuscio, Alessio Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition 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 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. |
| title | IoUCert: Robustness Verification for Anchor-based Object Detectors |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03043 |