Machine Learning Technologies for Secure Vehicular Communication in Internet of Vehicles: Recent Advances and Applications

Table 3

Summary for secure IoV communications.

Year	Source	Approaches	Features	Advantages	Challenges	Citations
2020	IEEE	Fog-based identity authentication (FBIA)	Fog-based identity authentication scheme and deep learning	IoV real-time security monitoring	Dual authentication levels for access authentication and vehicles’ timing detection	Song et al. [86]
2020	IEEE	SVM-based classifier	Authentication scheme based on SVM	Secure access frequencies and progressive protection of trusted communications	Fast authentication mechanism for large-scale IoV	Hasan et al. [83]
2018	IEEE	Certificateless Short Signature Scheme (CLSS) and ML	Anonymous authentication scheme-based ML	Secure communication between vehicles and roadside units	Security under adaptively chosen message and ID attacks	Liu et al. [80]
2017	IEEE	Aggregate privacy-preserving authentication protocol; Multiplicative Secret Sharing (MSS) technique	Distributed aggregate signature mechanism	Secure vehicular network authentication and trusted authority	Trade-off between security and storage resource management	Memon et al. [81]
2016	Elsevier	Smart Adaptive Data Aggregation (SADA); machine learning-based data fusion and analysis	Adaptive data aggregation-based ML	Secure data exchange between vehicles	Fully automated switching to unknown vehicle	Islam et al. [82]