| Paper ID | D-2-1.3 |
| Paper Title |
Prediction Method of Malware Infection Spreading Considering Network Scale |
| Authors |
Yurina Nagasawa, Keita Kishioka, Kansai University, Japan; Tomotaka Kimura, Doshisha University, Japan; Kouji Hirata, Kansai University, Japan |
| Session |
D-2-1: Digital Convergence of 5G, AIoT and Security I |
| Time | Wednesday, 09 December, 12:30 - 14:00 |
| Presentation Time: | Wednesday, 09 December, 13:00 - 13:15 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
| Topic |
Wireless Communications and Networking (WCN): Special Session: Digital Convergence of 5G, AIoT and Security |
| Abstract |
In the past, a malware epidemic model based on overlay networks consisting of hosts has been considered. Furthermore, based on the epidemic model, the degree of infection spreading has been estimated through simulation experiments. However, the computation time of the simulation experiment is very long for large-scale networks. To resolve this problem, a prediction method of malware infection spreading using a convolutional neural network (CNN) has been proposed, assuming that the method is applied to fixed-size networks. To extend this work, in this paper, we propose a method to predict the malware spreading with CNN, considering the network scale. The proposed method resizes images without losing information on network structures. By using the resized images as input data to CNN, the proposed method predicts the malware spreading for networks of different scales based on the information on the small networks. Through experimental evaluation, this paper shows the effectiveness of the proposed method. |