Reconstruction-Based Adversarial Attack Detection in Vision-Based Autonomous Driving Systems
Machine Learning and Knowledge Extraction · 07.11.2023 · 5 (4) · 1589-1611
DOI: 10.3390/make5040080 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 07.11.2023. Verfasst von Manzoor Hussain und 1 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education.
Abstract (Originalsprache)
The perception system is a safety-critical component that directly impacts the overall safety of autonomous driving systems (ADSs). It is imperative to ensure the robustness of the deep-learning model used in the perception system. However, studies have shown that these models are highly vulnerable to the adversarial perturbation of input data. The existing works mainly focused on studying the impact of these adversarial attacks on classification rather than regression models. Therefore, this paper first introduces two generalized methods for perturbation-based attacks: (1) We used naturally occurring noises to create perturbations in the input data. (2) We introduce a modified square, HopSkipJump, and decision-based/boundary attack to attack the regression models used in ADSs. Then, we propose a deep-autoencoder-based adversarial attack detector. In addition to offline evaluation metrics (e.g., F1 score and precision, etc.), we introduce an online evaluation framework to evaluate the robustness of the model under attack. The framework considers the reconstruction loss of the deep autoencoder that validates the robustness of the models under attack in an end-to-end fashion at runtime. Our experimental results showed that the proposed adversarial attack detector could detect square, HopSkipJump, and decision-based/boundary attacks with a true positive rate (TPR) of 93%.
Förderung
- Ministry of Education
Zitieren
APA
Hussain, M., & Hong, J. (2023). Reconstruction-Based Adversarial Attack Detection in Vision-Based Autonomous Driving Systems. Machine Learning and Knowledge Extraction, 5(4), 1589-1611. https://doi.org/10.3390/make5040080
Vancouver
Hussain M, Hong J. Reconstruction-Based Adversarial Attack Detection in Vision-Based Autonomous Driving Systems. Machine Learning and Knowledge Extraction. 2023;5(4):1589-1611. doi:10.3390/make5040080
BibTeX
@article{Hussain2023,
author = {Hussain, Manzoor and Hong, Jang-Eui},
title = {Reconstruction-Based Adversarial Attack Detection in Vision-Based Autonomous Driving Systems},
journal = {Machine Learning and Knowledge Extraction},
year = {2023},
volume = {5},
number = {4},
pages = {1589--1611},
doi = {10.3390/make5040080}
}
EUVIMED