Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving

The fast development of deep learning (DL) enables even resource-constrained devices to tackle complex artificial intelligence (AI) tasks, especially those related to environment perception in autonomous driving systems (ADS). However, AI models deployed in the real world are exposed to the threats...

Full description

Saved in:
Bibliographic Details
Main Authors: Lijun Chi, Mounira Msahli
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10879251/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241684154089472
author Lijun Chi
Mounira Msahli
author_facet Lijun Chi
Mounira Msahli
author_sort Lijun Chi
collection DOAJ
description The fast development of deep learning (DL) enables even resource-constrained devices to tackle complex artificial intelligence (AI) tasks, especially those related to environment perception in autonomous driving systems (ADS). However, AI models deployed in the real world are exposed to the threats of adversarial examples (AE). One specific type of physical attack utilizes laser beams or spots planted on images rather than crafted pixel-level perturbations to manipulate the victim deep neural networks (DNN) prediction. These attacks easily mislead traffic sign recognition and object detection in ADS. Laser-based adversarial attacks are cognitively stealthy but visually conspicuous, invalidating the previous defenses designed for digital attacks. This study considers two state-of-the-art (SOTA) laser-based attacks and establishes a benchmark comprising thousands of AEs. Such AEs have distinct pattern features, significant occupation, high contrast, and low variance. Based on the observation, a lightweight detection framework, Laser Guard, is proposed. Specifically, preprocessing methods are used to approximate the laser-perturbed areas, followed by a statistics-based strategy to determine abnormalities in the given samples. This framework can be applied in a plug-and-play manner with DNNs in intelligent vehicles. Extensive experimental results show that the framework can effectively filter out about 70-75% of laser-based street sign AEs, and extends well to other objects, successfully filtering out 80%. The detection latency of objects AEs is marginal, with the average detection time for laser spots being approximately 24 ms, and for laser beams, it is around 57 ms.
format Article
id doaj-art-1edc7cb9f3d34a07b3869b66097c1197
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1edc7cb9f3d34a07b3869b66097c11972025-08-20T02:00:32ZengIEEEIEEE Access2169-35362025-01-0113352193522910.1109/ACCESS.2025.354065310879251Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous DrivingLijun Chi0https://orcid.org/0009-0000-0905-9031Mounira Msahli1https://orcid.org/0000-0003-0331-493XLTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, FranceLTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, FranceThe fast development of deep learning (DL) enables even resource-constrained devices to tackle complex artificial intelligence (AI) tasks, especially those related to environment perception in autonomous driving systems (ADS). However, AI models deployed in the real world are exposed to the threats of adversarial examples (AE). One specific type of physical attack utilizes laser beams or spots planted on images rather than crafted pixel-level perturbations to manipulate the victim deep neural networks (DNN) prediction. These attacks easily mislead traffic sign recognition and object detection in ADS. Laser-based adversarial attacks are cognitively stealthy but visually conspicuous, invalidating the previous defenses designed for digital attacks. This study considers two state-of-the-art (SOTA) laser-based attacks and establishes a benchmark comprising thousands of AEs. Such AEs have distinct pattern features, significant occupation, high contrast, and low variance. Based on the observation, a lightweight detection framework, Laser Guard, is proposed. Specifically, preprocessing methods are used to approximate the laser-perturbed areas, followed by a statistics-based strategy to determine abnormalities in the given samples. This framework can be applied in a plug-and-play manner with DNNs in intelligent vehicles. Extensive experimental results show that the framework can effectively filter out about 70-75% of laser-based street sign AEs, and extends well to other objects, successfully filtering out 80%. The detection latency of objects AEs is marginal, with the average detection time for laser spots being approximately 24 ms, and for laser beams, it is around 57 ms.https://ieeexplore.ieee.org/document/10879251/Deep learningadversarial attacksdetection-based defenselaser-based attackspreprocessing
spellingShingle Lijun Chi
Mounira Msahli
Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving
IEEE Access
Deep learning
adversarial attacks
detection-based defense
laser-based attacks
preprocessing
title Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving
title_full Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving
title_fullStr Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving
title_full_unstemmed Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving
title_short Laser Guard: Efficiently Detecting Laser-Based Physical Adversarial Attacks in Autonomous Driving
title_sort laser guard efficiently detecting laser based physical adversarial attacks in autonomous driving
topic Deep learning
adversarial attacks
detection-based defense
laser-based attacks
preprocessing
url https://ieeexplore.ieee.org/document/10879251/
work_keys_str_mv AT lijunchi laserguardefficientlydetectinglaserbasedphysicaladversarialattacksinautonomousdriving
AT mouniramsahli laserguardefficientlydetectinglaserbasedphysicaladversarialattacksinautonomousdriving