Interactive Adversarial Testing of Autonomous Vehicles with Adjustable Confrontation Intensity

TL;DR

This paper introduces ExamPPO, an interactive adversarial testing framework for autonomous vehicles that adaptively modulates confrontation intensity to systematically evaluate AV robustness across diverse scenarios.

Contribution

The paper presents a novel, scenario-adaptive testing framework with adjustable confrontation intensity, enhancing the evaluation of AV safety and decision-making robustness.

Findings

Effectively modulates adversarial behavior to expose AV weaknesses

Generalizes across multiple scenarios and environments

Provides a systematic, reproducible evaluation method

Abstract

Scientific testing techniques are essential for ensuring the safe operation of autonomous vehicles (AVs), with high-risk, highly interactive scenarios being a primary focus. To address the limitations of existing testing methods, such as their heavy reliance on high-quality test data, weak interaction capabilities, and low adversarial robustness, this paper proposes ExamPPO, an interactive adversarial testing framework that enables scenario-adaptive and intensity-controllable evaluation of autonomous vehicles. The framework models the Surrounding Vehicle (SV) as an intelligent examiner, equipped with a multi-head attention-enhanced policy network, enabling context-sensitive and sustained behavioral interventions. A scalar confrontation factor is introduced to modulate the intensity of adversarial behaviors, allowing continuous, fine-grained adjustment of test difficulty. Coupled with structured evaluation metrics, ExamPPO systematically probes AV's robustness across diverse scenarios and strategies. Extensive experiments across multiple scenarios and AV strategies demonstrate that ExamPPO can effectively modulate adversarial behavior, expose decision-making weaknesses in tested AVs, and generalize across heterogeneous environments, thereby offering a unified and reproducible solution for evaluating the safety and intelligence of autonomous decision-making systems.