Formal Verification of Deep Neural Networks for Object Detection

TL;DR

This paper extends formal verification methods from image classification to object detection models, demonstrating how to identify vulnerabilities and improve robustness in complex computer vision tasks.

Contribution

It introduces a new formulation for verifying object detection models and adapts existing verification tools to this domain, filling a gap in current research.

Findings

Verification uncovers vulnerabilities in object detection models

Existing tools can be adapted for object detection verification

Highlights the need for further verification research in computer vision

Abstract

Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing model robustness and reliability. While most existing verification methods focus on image classification models, this work extends formal verification to the more complex domain of emph{object detection} models. We propose a formulation for verifying the robustness of such models and demonstrate how state-of-the-art verification tools, originally developed for classification, can be adapted for this purpose. Our experiments, conducted on various datasets and networks, highlight the ability of formal verification to uncover vulnerabilities in object detection models, underscoring the need to extend verification efforts to this domain. This work lays the foundation for further research into formal verification across a broader range of computer vision applications.