Uncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks

TL;DR

This paper introduces TUQCP, a framework that enhances the robustness of collaborative object detection against adversarial attacks by combining adversarial training with uncertainty quantification techniques, significantly improving detection accuracy.

Contribution

It proposes a novel framework that integrates adversarial training and uncertainty estimation to improve the resilience of collaborative object detection models under attack.

Findings

Achieves 80.41% improvement in detection accuracy under adversarial attacks.

Demonstrates effectiveness of uncertainty quantification in adversarial robustness.

Applicable to various collaborative and single-agent detection models.

Abstract

Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities, and improve object detection accuracy compared with individual perception. However, adversarial attacks pose a potential threat to the deep learning COD models, and introduce high output uncertainty. With unknown attack models, it becomes even more challenging to improve COD resiliency and quantify the output uncertainty for highly dynamic perception scenes such as autonomous vehicles. In this study, we propose the Trusted Uncertainty Quantification in Collaborative Perception framework (TUQCP). TUQCP leverages both adversarial training and uncertainty quantification techniques to enhance the adversarial robustness of existing COD models. More specifically, TUQCP first adds perturbations to the shared information of randomly selected agents during object detection collaboration by adversarial training. TUQCP then alleviates the impacts of adversarial attacks by providing output uncertainty estimation through learning-based module and uncertainty calibration through conformal prediction. Our framework works for early and intermediate collaboration COD models and single-agent object detection models. We evaluate TUQCP on V2X-Sim, a comprehensive collaborative perception dataset for autonomous driving, and demonstrate a 80.41% improvement in object detection accuracy compared to the baselines under the same adversarial attacks. TUQCP demonstrates the importance of uncertainty quantification to COD under adversarial attacks.