
Securing Connected & Autonomous Vehicles: Challenges posed by Adversarial Machine Learning and the way forward
Author(s) -
S. Kiruthika,
A. Aashin,
K. S. Gopinath,
A. Gowtham
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1916/1/012110
Subject(s) - adversarial machine learning , artificial intelligence , machine learning , computer science , adversarial system , computer security , pipeline (software) , selection (genetic algorithm) , enhanced data rates for gsm evolution , risk analysis (engineering) , business , programming language
Associated and self-ruling automobiles (CAVs) will shape a foundation for the future cutting edge canny transport frameworks (ITS) giving comfortable travelling, street wellbeing, alongside various worth added administrations. Such a change—which would be fuelled by attendant advances on advances for AI (Machine Learning) and remote interchanges—will empower a future vehicular biological system that is better included and more effective. Notwithstanding and are sneaking security issues identified with the utilization of Machine Learning in a particularly basic setting where a mistaken Machine Learning choice may not exclusively be an aggravation yet can prompt loss of valuable lives. Here it’s present a top to bottom outline of the different difficulties related with the utilization of Machine Learning In vehicular organizations. Moreover, we form the Machine Learning Pipeline of CAVs and present different potential security issues related with the selection of Machine Learning Strategies. Specifically, it’s center around the point of view of antagonistic Machine Learning Assaults on CAVs and framework an answer for protecting against ill-disposed assaults in different settings.