This study proposes the wider use of non-intrusive side-channel power data in cybersecurity for intrusion detection. An in-depth analysis of side-channel IoT power behaviour is performed on two well-known IoT devices—a Raspberry Pi 3 model B and a DragonBoard 410c—operating under normal conditions and under attack. Attacks from the categories of reconnaissance, brute force and denial of service are applied, and the side-channel power data of the IoT testbeds are then studied in detail. These attacks are used together to further compromise the IoT testbeds in a “capture-the-flag scenario”, where the attacker aims to infiltrate the device and retrieve a secret file. Some clear similarities in the side-channel power signatures of these attacks can be seen across the two devices. Furthermore, using the knowledge gained from studying the features of these attacks individually and the signatures witnessed in the “capture the flag scenario”, we show that security teams can reverse engineer attacks applied to their system to achieve a much greater understanding of the events that occurred during a breach. While this study presents behaviour signatures analysed visually, the acquired power series datasets will be instrumental for future human-centred AI-assisted intrusion detection.
This study proposes a heterogeneous hardware-based framework for network intrusion detection using lightweight artificial neural network models. With the increase in the volume of exchanged data, IoT networks’ security has become a crucial issue. Anomaly-based intrusion detection systems (IDS) using machine learning have recently gained increased popularity due to their generation’s ability to detect unseen attacks. However, the deployment of anomaly-based AI-assisted IDS for IoT devices is computationally expensive. A high-performance and ultra-low power consumption anomaly-based IDS framework is proposed and evaluated in this paper. The framework has achieved the highest accuracy of 98.57% and 99.66% on the UNSW-NB15 and IoT-23 datasets, respectively. The inference engine on the MAX78000EVKIT AI-microcontroller is 11.3 times faster than the Intel Core i7-9750H 2.6 GHz and 21.3 times faster than NVIDIA GeForce GTX 1650 graphics cards, when the power drawn was 18mW. In addition, the pipelined design on the PYNQ-Z2 SoC FPGA board with the Xilinx Zynq xc7z020-1clg400c device is optimised to run at the on-chip frequency (100 MHz), which shows a speedup of 53.5 times compared to the MAX78000EVKIT.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.