Benchmarking Lightweight Deep Learning Models for In-Vehicle Face Anti-Spoofing
Michael Anthony Ruiz, Soodeh Nikan · 2025
In-vehicle face anti-spoofing (FAS) is a crucial security requirement for automotive facial authentication systems in modern cars. Given the demanding cabin environments and limited computational resources, VFPAD (in-Vehicle Face Presentation Attack Detection) dataset, a benchmark for NIR (near infrared)-based in-vehicle presentation attack detection, is used in this case study to evaluate six lightweight deep learning architectures: FeatherNetB, MobileNetV3-small, MiniFASNetV2, MobileNetV4-small, MobileViTV3-XS, and EfficientNetV2-B0. Using a consistent training protocol with transfer learning and fine-tuning, we assess each model according to its classification performance (average classification error rate (ACER), accuracy, and F1 score) and efficiency (floating point operations per second (FLOPS) and number of model parameters). According to experimental results, more recent mobile-oriented deep neural networks (DNNs)-MobileNetV4 and EfficientNetV2-B0 in particular-perform better than older and transformer-based designs, achieving ACERs as low as 0.0086 while keeping latency and model sizes small. Our results highlight the feasibility of implementing real-time FAS systems in vehicular environments with contemporary lightweight architectures.