Comparative Research Based on Internet Worms

DOI

10.2991/978-94-6463-471-6_93How to use a DOI?

Keywords

Internet worms; Intrusion detection system (IDS); Hybrid long short-term memory; Deep Learning

Abstract

Strong detection and categorization frameworks are required since the threat on internet worms is still a top issue in the field of cyber security. In this comparative study, we compare and contrast the Deep Learning CNN Framework & the Joint Detection and Classification of Signature and NetFlow inspired Internet Worms using MBGWO-based Hybrid LSTM techniques for detecting and classifying internet worms. Convolutional Neural Networks (CNNs) are used by the Deep Learning CNN Framework to extract and learn complex information from network traffic data related to worms. This framework seeks to accomplish precise worm identification and classification by utilising deep learning. To evaluate the success of the Deep Learning CNN Framework, we examine its design, training procedure, and performance measures. On the other hand, the Joint Detection and Classification strategy combines MBGWO (Modified Grey Wolf Optimization)-based Hybrid LSTM (Long Short-Term Memory) model with Signature and NetFlow-based techniques. The advantages of flow-based analysis, signature-based detection, and the LSTM model’s capacity to detect temporal dependencies are all combined in this hybrid technique. We look into this approach’s essential elements, optimisation plan, and performance results. We assess the benefits, drawbacks, and overall effectiveness between the two frameworks with regard to of detection precision, recall, accuracy, and F1-score through a comparison analysis. We also evaluate their viability, effectiveness, and possibility of real-world application. The results of this study aid in and understanding the various methods of internet worm detection. We offer insights into the developments, difficulties, and potential future directions in this important field of cyber security by looking at the Deep Learning CNN Framework and the Joint Detection and Classification technique. The creation of stronger and more effective frameworks for thwarting internet worms and protecting network infrastructures is guided by the comparative analysis.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Mundlamuri Venkata Rao
AU  - Divya Midhunchakkaravarthy
AU  - Sujatha Dandu
PY  - 2024
DA  - 2024/07/30
TI  - Comparative Research Based on Internet Worms
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 969
EP  - 976
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_93
DO  - 10.2991/978-94-6463-471-6_93
ID  - Rao2024
ER  -