Safety Interventions against Adversarial Patches in an Open-Source Driver Assistance System

2025-04-26

AI Summary

This study systematically evaluates the security resilience of Advanced Driver Assistance Systems (ADAS) against adversarial patch attacks targeting the perception layer. We develop an end-to-end testing framework based on the production-grade OpenPilot stack, enabling adversarial patch injection, real-time sensor input monitoring, tiered safety intervention triggering, and human–machine takeover latency modeling. We propose an intervention timing-sensitivity analysis method and a dynamic arbitration framework for resolving conflicts among heterogeneous safety mechanisms—first quantifying adversarial patch impact in量产-level ADAS. Experiments show that timely human takeover reduces crash probability by 87%; automated interventions decrease lateral control failure risk by 63%; and our arbitration framework effectively resolves 32% of latent conflicts across three intervention strategies. The core contribution is a novel paradigm for ADAS resilience assessment and coordinated defense against perception-layer adversarial attacks.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Adversarial Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Drivers are becoming increasingly reliant on advanced driver assistance systems (ADAS) as autonomous driving technology becomes more popular and developed with advanced safety features to enhance road safety. However, the increasing complexity of the ADAS makes autonomous vehicles (AVs) more exposed to attacks and accidental faults. In this paper, we evaluate the resilience of a widely used ADAS against safety-critical attacks that target perception inputs. Various safety mechanisms are simulated to assess their impact on mitigating attacks and enhancing ADAS resilience. Experimental results highlight the importance of timely intervention by human drivers and automated safety mechanisms in preventing accidents in both driving and lateral directions and the need to resolve conflicts among safety interventions to enhance system resilience and reliability.

Problem

• Evaluating ADAS resilience against adversarial perception attacks
• Assessing safety mechanisms for mitigating attacks on autonomous vehicles
• Resolving conflicts among safety interventions to enhance system reliability

Innovation

• Simulate safety mechanisms for ADAS resilience
• Assess human and automated intervention impact
• Resolve conflicts among safety interventions