On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems
Sensors · 29.05.2024 · 24 (11) · 3515
DOI: 10.3390/s24113515 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2024. Verfasst von Sazid Nazat und 2 weiteren Autor:innen. Beteiligte Einrichtung: Electrical and Computer Engineering Department, Purdue School of Engineering and Technology, Indiana University-Purdue University Indianapolis, India…. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lilly Endowment, Indiana University, Enhanced Mentoring Program with Opportunities for Ways to Excel in Research (EMPOWER).
Abstract (Originalsprache)
The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Electrical and Computer Engineering Department, Purdue School of Engineering and Technology, Indiana University-Purdue University Indianapolis, Indianapolis, IN 46202, USA.
- Computer and Information Technology Department, Purdue School of Engineering and Technology, Indiana University-Purdue University Indianapolis, Indianapolis, IN 46202, USA.
ORCID-Profile: Sazid Nazat, Osvaldo Arreche, Mustafa Abdallah
Förderung
- Lilly Endowment
- Indiana University
- Enhanced Mentoring Program with Opportunities for Ways to Excel in Research (EMPOWER)
- Indiana University–Purdue University Indianapolis
- Lilly Endowment, Inc.
Zitieren
APA
Nazat, S., Arreche, O., & Abdallah, M. (2024). On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems. Sensors, 24(11), 3515. https://doi.org/10.3390/s24113515
Vancouver
Nazat S, Arreche O, Abdallah M. On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems. Sensors. 2024;24(11):3515. doi:10.3390/s24113515
BibTeX
@article{Nazat2024,
author = {Nazat, Sazid and Arreche, Osvaldo and Abdallah, Mustafa},
title = {On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems},
journal = {Sensors},
year = {2024},
volume = {24},
number = {11},
pages = {3515},
doi = {10.3390/s24113515}
}
EUVIMED