Interventional Root Cause Analysis of Failures in Multi-Sensor Fusion Perception Systems
Shuguang Wang
Network and Distributed System Security (NDSS) Symposium 2025 · Day 2 · Sensor Attacks
Autonomous driving systems, particularly their perception modules, are critical for safe and reliable operation. These systems rely on **multi-sensor fusion** to process data from various sensors like LiDAR and cameras in real-time, building a comprehensive understanding of their surroundings. However, perception systems are not infallible; faults within sub-modules can lead to severe issues such as **missing obstacles** or **ghost obstacles**, dramatically increasing collision risks and leading to unpredictable driving decisions. This talk by Shuguang Wang introduces a novel approach to perform **root cause analysis (RCA)** on these complex perception failures.
AI review
Legitimate systems-security research applying causal inference to autonomous driving perception failures — DAG-based intervention framework, cross-platform validation on Autoware and Apollo, real-world confirmation from developers. Solid academic contribution, but the security angle is thin and the novelty ceiling is modest; causal graph approaches to RCA aren't new, and the AV-specific adaptation, while competent, doesn't dramatically advance the state of the art.