Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach
Abstract
Object detection systems are essential in safety-critical applications, but they are vulnerable to object disappearance (OD) threats, in which valid objects become undetected under small input perturbations, creating serious risks. This paper addresses the problem of verifying the robustness of YOLO (You Only Look Once) networks against OD by proposing a three-step probabilistic verification framework: (1) estimating output ranges under a distribution of input perturbations, (2) formally verifying the Non-Maximum Suppression (NMS) process within these ranges, and (3) iteratively refining the results to reduce over-approximation. The framework scales to practical YOLO models. Both theoretical analysis and experimental results demonstrate that our method achieves comparable probabilistic guarantees and provides tighter Intersection-over-Union (IoU) lower bounds while requiring significantly fewer samples than existing methods.
Cite
Text
Liu et al. "Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach." International Conference on Learning Representations, 2026.Markdown
[Liu et al. "Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/liu2026iclr-certifying/)BibTeX
@inproceedings{liu2026iclr-certifying,
title = {{Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach}},
author = {Liu, Zongxin and Chi, Zhiming and Yu, Lijia and Lin, Tao and Zhang, Lijun},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/liu2026iclr-certifying/}
}