Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Martinez, Yago Romano, Carter, Brady, Solanki, Abhijeet, Amiri, Wesam Al, Hasan, Syed Rafay, Guo, Terry N.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2502.05208
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908452289249280
author Martinez, Yago Romano
Carter, Brady
Solanki, Abhijeet
Amiri, Wesam Al
Hasan, Syed Rafay
Guo, Terry N.
author_facet Martinez, Yago Romano
Carter, Brady
Solanki, Abhijeet
Amiri, Wesam Al
Hasan, Syed Rafay
Guo, Terry N.
contents Autonomous vehicles (AVs) rely heavily on cameras and artificial intelligence (AI) to make safe and accurate driving decisions. However, since AI is the core enabling technology, this raises serious cyber threats that hinder the large-scale adoption of AVs. Therefore, it becomes crucial to analyze the resilience of AV security systems against sophisticated attacks that manipulate camera inputs, deceiving AI models. In this paper, we develop camera-camouflaged adversarial attacks targeting traffic sign recognition (TSR) in AVs. Specifically, if the attack is initiated by modifying the texture of a stop sign to fool the AV's object detection system, thereby affecting the AV actuators. The attack's effectiveness is tested using the CARLA AV simulator and the results show that such an attack can delay the auto-braking response to the stop sign, resulting in potential safety issues. We conduct extensive experiments under various conditions, confirming that our new attack is effective and robust. Additionally, we address the attack by presenting mitigation strategies. The proposed attack and defense methods are applicable to other end-to-end trained autonomous cyber-physical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mitigation of Camouflaged Adversarial Attacks in Autonomous Vehicles--A Case Study Using CARLA Simulator
Martinez, Yago Romano
Carter, Brady
Solanki, Abhijeet
Amiri, Wesam Al
Hasan, Syed Rafay
Guo, Terry N.
Cryptography and Security
Artificial Intelligence
Machine Learning
Autonomous vehicles (AVs) rely heavily on cameras and artificial intelligence (AI) to make safe and accurate driving decisions. However, since AI is the core enabling technology, this raises serious cyber threats that hinder the large-scale adoption of AVs. Therefore, it becomes crucial to analyze the resilience of AV security systems against sophisticated attacks that manipulate camera inputs, deceiving AI models. In this paper, we develop camera-camouflaged adversarial attacks targeting traffic sign recognition (TSR) in AVs. Specifically, if the attack is initiated by modifying the texture of a stop sign to fool the AV's object detection system, thereby affecting the AV actuators. The attack's effectiveness is tested using the CARLA AV simulator and the results show that such an attack can delay the auto-braking response to the stop sign, resulting in potential safety issues. We conduct extensive experiments under various conditions, confirming that our new attack is effective and robust. Additionally, we address the attack by presenting mitigation strategies. The proposed attack and defense methods are applicable to other end-to-end trained autonomous cyber-physical systems.
title Mitigation of Camouflaged Adversarial Attacks in Autonomous Vehicles--A Case Study Using CARLA Simulator
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.05208