Generating adversarial driving scenarios is critical for evaluating and improving autonomous vehicle decision-making systems in simulation. Recent approaches, such as ChatScene and LLM-Attacker, rely primarily on the prior knowledge of Large Language Models and Vision-Language Models to generate driving scenarios procedurally. We argue that adversarial scenes should be generated based on the failure diagnosis (e.g., indecisiveness, multi-frame inconsistency) of the driving policy to specifically address the policy's weaknesses instead of relying on prior assumptions. In this paper, we propose SPHINX, a closed-loop framework for adversarial scenario synthesis guided by a simple principle: first explain, then explore. Beyond blindly exploring the scenario space, SPHINX leverages explainable artificial intelligence methods to analyze the policy, identifying key visual concepts and their influence on policy outputs, and the uncertainty of the decisions. Given the interpretable evidence extracted from the policy's own decision process, we use a vision language model to rationalize and criticize failure modes of the current policy. These critics are then used to generate targeted adversarial scenarios for policy retraining and improvement. We demonstrate that SPHINX can highlight an interpretable account of policy failures while other adversarial scene generation cannot. Across the evaluated benchmarks and test suites, SPHINX can be applied to diverse state-of-the-art autonomous vehicle architectures and yields consistent robustness improvements over existing scenario-generation methods.

翻译：生成对抗性驾驶场景对于在仿真环境中评估和改进自动驾驶决策系统至关重要。近期方法，如ChatScene和LLM-Attacker，主要依赖大语言模型和视觉语言模型的先验知识来程序化生成驾驶场景。我们认为，对抗性场景应基于驾驶策略的故障诊断（例如，犹豫不决、多帧不一致性）来生成，以专门应对策略的弱点，而非依赖先验假设。本文提出SPHINX，一种遵循“先解释，后探索”简单原则的闭环对抗性场景合成框架。SPHINX并不盲目探索场景空间，而是利用可解释人工智能方法分析驾驶策略，识别关键视觉概念及其对策略输出的影响，以及决策的不确定性。基于从策略自身决策过程中提取的可解释性证据，我们使用视觉语言模型对当前策略的失效模式进行合理化分析与批判。随后，这些批判性分析被用于生成有针对性的对抗性场景，以促进策略的再训练与改进。我们证明，SPHINX能够突出呈现策略失效的可解释性说明，而其他对抗性场景生成方法则无法做到。在多个评估基准与测试套件中，SPHINX可应用于多种最先进的自动驾驶架构，并在现有场景生成方法基础上实现一致的鲁棒性提升。