Towards Robust IoT Defense: Comparative Statistics of Attack Detection in Resource-Constrained Scenarios

TL;DR

This paper evaluates and compares lightweight and TinyML-based attack detection algorithms for resource-constrained IoT devices, introducing a novel protocol data analysis method that enhances attack detection accuracy and efficiency.

Contribution

It presents a comprehensive statistical comparison of existing algorithms and introduces a new detection method analyzing protocol data for resource-constrained IoT security.

Findings

Proposed algorithms achieve over 99% accuracy.

Dynamic classifier selection improves detection performance.

Novel protocol data analysis enhances attack detection accuracy.

Abstract

Resource constraints pose a significant cybersecurity threat to IoT smart devices, making them vulnerable to various attacks, including those targeting energy and memory. This study underscores the need for innovative security measures due to resource-related incidents in smart devices. In this paper, we conduct an extensive statistical analysis of cyberattack detection algorithms under resource constraints to identify the most efficient one. Our research involves a comparative analysis of various algorithms, including those from our previous work. We specifically compare a lightweight algorithm for detecting resource-constrained cyberattacks with another designed for the same purpose. The latter employs TinyML for detection. In addition to the comprehensive evaluation of the proposed algorithms, we introduced a novel detection method for resource-constrained attacks. This method involves analyzing protocol data and categorizing the final data packet as normal or attacked. The attacked data is further analyzed in terms of the memory and energy consumption of the devices to determine whether it is an energy or memory attack or another form of malicious activity. We compare the suggested algorithm performance using four evaluation metrics: accuracy, PoD, PoFA, and PoM. The proposed dynamic techniques dynamically select the classifier with the best results for detecting attacks, ensuring optimal performance even within resource-constrained IoT environments. The results indicate that the proposed algorithms outperform the existing works with accuracy for algorithms with TinyML and without TinyML of 99.3\%, 98.2\%, a probability of detection of 99.4\%, 97.3\%, a probability of false alarm of 1.23\%, 1.64\%, a probability of misdetection of 1.64\%, 1.46 respectively. In contrast, the accuracy of the novel detection mechanism exceeds 99.5\% for RF and 97\% for SVM.