Efficient Autonomous Defense System Using Machine Learning on Edge Device

Jaehyuk Cho

doi:10.32604/cmc.2022.020826

Abstract

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

Highlights

Centralized computing structures have large data volumes such as smart factories, smart farms, and self-driving cars
We study to increase the security of hardware by detecting power anomalies, signal anomalies, and clock(clk) anomalies in field programmable gate array (FPGA) and controlling communication methods according to priorities
FPGA can adapt to all algorithmic properties due to hardware flexibility, which is different from Central Processing Unit (CPU) and Graphics Processing Unit (GPU) that mainly utilize spatial parallel processing

Summary

Introduction

Centralized computing structures have large data volumes such as smart factories, smart farms, and self-driving cars. There is a problem to ask for real-time processing, such as overloading cloud servers due to network traffic. To solve this problem, edge computing technologies that process data in real-time or near-field are gaining attention [1]. As the utilization of edge computing facilitates smart convergence across the infrastructure, the surface of cybersecurity expands [2,3,4]. It increases the threat posed by cyberattacks such as system compromise, service interruption, and information leakage [5,6]. The possibility of cyberattacks on drones and self-driving cars along with IoT is expanding beyond the scope of

Methods

Results

Discussion

Conclusion