Evaluating Online Learning Anomaly Detection on Intel Neuromorphic Chip and Memristor Characterization Tool

Automobile companies are focused on moving to connected, smart vehicles which it relates not only to privacy and usual security concerns, but to the safety of drivers and passengers. This matter shines the light on the need of building systems that can detect anomalies and zero-day attack for smart vehicles. The objective of this thesis is to develop an online learning in-vehicle anomaly detection system on neuromorphic Intel\u27s chip and build a cost-cutting and high-speed tester to measure real memristor device properties. The entire thesis work is divided into three tasks. Task 1 shows an offline learning converted Autoencoder-based model to spiking neural network for in-vehicle cyber-attack detection running on Loihi Chip, this work has been published [44]. Task 2 introduces an online learning anomaly detection system that can detect anomalies for car hacking identification using Intel\u27s Loihi low power device which can also be applied to many other tasks, such as fault detection, and financial data processing. Task 3 examines a built an FPGA-based tester for memristor device characterization, the typical approach is to use an analog testerwhich can be extremely expensive