Experimental Security Analysis of DNN-based Adaptive Cruise Control under Context-Aware Perception Attacks
Authors:
- Xugui ZhouXZXugui Zhou
- Haotian RenHRHaotian Ren
- Cristina Nita-RotaruCNCristina Nita-Rotaru
- Homa AlemzadehHAHoma Alemzadeh
Preprint
Abstract
Adaptive Cruise Control (ACC) is a widely used driver assistance feature for maintaining desired speed and safe distance to the leading vehicles. This paper evaluates the security of the deep neural network (DNN) based ACC systems under stealthy perception attacks that strategically inject perturbations into camera data to cause forward collisions. We present a combined knowledge-and-data-driven approach to design a context-aware strategy for the selection of the most critical times for triggering the attacks and a novel optimization-based method for the adaptive generation of image perturbations at run-time. We evaluate the effectiveness of the proposed attack using an actual driving dataset and a realistic simulation platform with the control software from a production ACC system and a physical-world driving simulator while considering interventions by the driver and safety features such as Automatic Emergency Braking (AEB) and Forward Collision Warning (FCW). Experimental results show that the proposed attack achieves 142.9x higher success rate in causing accidents than random attacks and is mitigated 89.6% less by the safety features while being stealthy and robust to real-world factors and dynamic changes in the environment. This study provides insights into the role of human operators and basic safety interventions in preventing attacks.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Hybrid Knowledge and Data Driven Synthesis of Runtime Monitors for Cyber-Physical SystemsIEEE Transactions on Dependable and Secure Computing, 2023
- A Formal Safety Characterization of Advanced Driver Assist Systems in the Car-Following Regime with Scenario-SamplingIFAC-PapersOnLine, 2022
- Autonomous Vehicle with Emergency Braking Algorithm Based on Multi-Sensor Fusion and Super Twisting Speed ControllerApplied Sciences, 2022
- Cybersecurity for autonomous vehicles: Review of attacks and defenseComputers & Security, 2021
- Multi-Object Detection and Tracking, Based on DNN, for Autonomous Vehicles: A ReviewIEEE Sensors Journal, 2020
- Driver brake response to sudden unintended acceleration while parkingTransportation Research Interdisciplinary Perspectives, 2019
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- A Trusted Safety Verifier for Process Controller Code2014
- Vehicle Classification Based on the Radar Measurement of Height ProfilesIEEE Transactions on Intelligent Transportation Systems, 2007
- A universal image quality indexIEEE Signal Processing Letters, 2002