Security-Aware Data-Driven Intelligent Transportation Systems

Intelligent transportation systems have been envisioned to bring more intelligence and cooperative sensing meet the imminent demands of overall improved autonomous transportation. However, dynamic era modern applications fixed architecture legacy Internet needs flexible, innovative, adaptive, programmable software defined intelligent (SD-ITS). The centralized control SD-ITS can be a potential primary target prevalent cyber threats attacks that simply throw entire network into chaos. authors propose DL-driven multi-vector scalable attack detection framework leveraging graphical processing unit (GPU) empowered Bidirectional Long Short-Term Memory (BLSTM) efficiently tackle exponentially growing diverse sophisticated primarily SD-ITS. proposed technique has rigorously evaluated with current state-of-the-art publicly available Flow-based dataset (i.e., CICIDS2017) using standard performance metrics. Further, mechanism is compared contemporary benchmarks DL algorithms). Extensive experimental results exhibit out-performance in term accuracy trivial trade-off computational complexity. Finally, study also employed 10-fold cross validation explicitly show unbiased results.