MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving

TL;DR

MetAdv is an innovative platform that combines virtual simulation and physical vehicle feedback to enable comprehensive, interactive adversarial testing of autonomous driving systems, enhancing safety evaluation and human-machine trust insights.

Contribution

Introduces MetAdv, a hybrid virtual-physical adversarial testing platform with a three-layer closed-loop environment supporting diverse AD tasks and real-time human feedback.

Findings

Supports realistic, dynamic adversarial testing environments.

Enables real-time physiological and behavioral feedback collection.

Facilitates end-to-end evaluation from simulation to physical deployment.

Abstract

Evaluating and ensuring the adversarial robustness of autonomous driving (AD) systems is a critical and unresolved challenge. This paper introduces MetAdv, a novel adversarial testing platform that enables realistic, dynamic, and interactive evaluation by tightly integrating virtual simulation with physical vehicle feedback. At its core, MetAdv establishes a hybrid virtual-physical sandbox, within which we design a three-layer closed-loop testing environment with dynamic adversarial test evolution. This architecture facilitates end-to-end adversarial evaluation, ranging from high-level unified adversarial generation, through mid-level simulation-based interaction, to low-level execution on physical vehicles. Additionally, MetAdv supports a broad spectrum of AD tasks, algorithmic paradigms (e.g., modular deep learning pipelines, end-to-end learning, vision-language models). It supports flexible 3D vehicle modeling and seamless transitions between simulated and physical environments, with built-in compatibility for commercial platforms such as Apollo and Tesla. A key feature of MetAdv is its human-in-the-loop capability: besides flexible environmental configuration for more customized evaluation, it enables real-time capture of physiological signals and behavioral feedback from drivers, offering new insights into human-machine trust under adversarial conditions. We believe MetAdv can offer a scalable and unified framework for adversarial assessment, paving the way for safer AD.