Authors:
André Proto
1
;
Charles Miers
2
and
Tereza C. M. B. Carvalho
1
Affiliations:
1
Laboratory of Sustainability in ICT, University of São Paulo (USP), Brazil
;
2
Graduate Program in Applied Computing (PPGCA), Santa Catarina State University (UDESC), Brazil
Keyword(s):
Energy Depletion Attacks, LoRaWAN, Distance Metrics, Intrusion Detection, Lightweight Architecture.
Abstract:
LoRaWAN emerges as a promising technology for deploying low-power sensors to tackle industrial and urban challenges. However, Energy Depletion Attacks (EDAs) presents a substantial threat to sensors operating within the LoRaWAN framework. Various attacks, including jamming, replay attacks, firmware manipulation, and application vulnerabilities in Internet of Things systems, have the potential to induce energy depletion. Some of them are regarded as silent attacks, characterized by the absence or minimal occurrence of network traffic, rendering their detection challenging. In response to this challenge, our research introduces an architecture designed to detect EDAs in LoRaWAN sensors. We propose an implementation of a lightweight and energy-efficient intrusion detection system developed for resource-constrained devices. Our solution applies distance metrics to detect anomaly behaviours in the energy consumption patterns of sensors. In order to assess the viability of our proposed met
hodology, we employ the F1 score as an evaluative metric that demonstrates the efficiency of its intrusion detection accuracy of EDAs. Thus, our proposal diverges from the traditional approaches relying on network traffic analysis for intrusion detection, opting instead for a focus on the analysis of energy consumption data.
(More)