Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach

Zongxin Liu, Lijia Yu, Tao Lin, Zhiming Chi, Lijun Zhang

Keywords: Probabilistic Verification, Formal Verification, Object Detection, Safety Guaranteen

TL;DR: This paper presents a probabilistic framework to verify the entire YOLO pipeline against perturbations, uniquely incorporating a formal analysis of previously under-explored Non-Maximum Suppression (NMS) post-processing stage.

Abstract: Object detection systems are essential in safety-critical applications, but they are vulnerable to object disappearance (OD) threat, in which valid objects become undetected under small input perturbations, creating serious risks. This paper addresses the problem of verifying the robustness of YOLO 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.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 1307