Learning the Propagation of Worms in Wireless Sensor Networks

TL;DR

This paper develops a neural network-based model to analyze and predict the propagation dynamics of worms in wireless sensor networks, aiding in understanding and defending against such attacks.

Contribution

It introduces a novel learning model combining complex neural networks to analytically derive worm propagation dynamics in WSNs.

Findings

Model accurately predicts worm spread behavior.

Neural network approach outperforms traditional models.

Analysis verified by experimental results.

Abstract

Wireless sensor networks (WSNs) are composed of spatially distributed sensors and are considered vulnerable to attacks by worms and their variants. Due to the distinct strategies of worms propagation, the dynamic behavior varies depending on the different features of the sensors. Modeling the spread of worms can help us understand the worm attack behaviors and analyze the propagation procedure. In this paper, we design a communication model under various worms. We aim to learn our proposed model to analytically derive the dynamics of competitive worms propagation. We develop a new searching space combined with complex neural network models. Furthermore, the experiment results verified our analysis and demonstrated the performance of our proposed learning algorithms.