Efficient Autonomous Defense System Using Machine Learning on Edge Device

As a large amount of data needs to be processed and speed improved, edge computing with ultra-low latency ultra-connectivity is emerging as new paradigm. These changes can lead cyber risks, should therefore considered for security threat model. To this end, we constructed an system study in two directions, hardware software. First, on the side, want autonomically defend against attacks such side channel by configuring field programmable gate array (FPGA) which suitable identifying communication status control method according priority. In addition, software collected server performs end-to-end encryption via symmetric keys. Also, modeled autonomous defense systems using machine learning targets incoming outgoing logs. Server log utilizes existing intrusion detection datasets that used real-world environments. was detect early modeling prevention identify behaviors violate policy, utilize set real environment. Through this, designed efficient provide stable detecting abnormal signals from device converting them effective computing, intrusions side.