Robustness Verification for Knowledge-Based Logic of Risky Driving Scenes
This work addresses safety-critical decision-making in AI for transportation, focusing on verifying logic to improve model reliability in risky driving scenarios, though it appears incremental as it applies existing verification methods to new data.
The authors tackled the problem of verifying the robustness of knowledge-based logic derived from risky driving scenes, using public transportation accident datasets to train Decision Tree and XGBoost models and applying automated verification methods under multiple parameter combinations.
Many decision-making scenarios in modern life benefit from the decision support of artificial intelligence algorithms, which focus on a data-driven philosophy and automated programs or systems. However, crucial decision issues related to security, fairness, and privacy should consider more human knowledge and principles to supervise such AI algorithms to reach more proper solutions and to benefit society more effectively. In this work, we extract knowledge-based logic that defines risky driving formats learned from public transportation accident datasets, which haven't been analyzed in detail to the best of our knowledge. More importantly, this knowledge is critical for recognizing traffic hazards and could supervise and improve AI models in safety-critical systems. Then we use automated verification methods to verify the robustness of such logic. More specifically, we gather 72 accident datasets from Data.gov and organize them by state. Further, we train Decision Tree and XGBoost models on each state's dataset, deriving accident judgment logic. Finally, we deploy robustness verification on these tree-based models under multiple parameter combinations.