Web Attack Detection Based on ResNet and RNN
- Authors
- Chen, Xin; Wu, Zhiqiang; Lee, Scott Uk-Jin
- Issue Date
- Apr-2019
- Publisher
- Mehran UET
- Keywords
- Web security; Web attack detection; convolutional neural network; ResNet; recurrent neural network; gated recurrent unit.
- Citation
- International Conference on Computational Sciences and Technologies, pp.64 - 67
- Journal Title
- International Conference on Computational Sciences and Technologies
- Start Page
- 64
- End Page
- 67
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/3025
- Abstract
- Web attack detection is an important part of web security. As our society already depends heavily on web technologies, web attacks can actually cause serious problems such as economic losses, data leakage, business interruption and even attacks on Internet of Thing devices that affect personal and social security. In order to prevent such disasters, we propose a web attack detection approach based on ResNet and Gate Recurrent Unit (GRU). In this approach, Word2vec is used to extract features of HTTP request URL with which detection model is trained using ResNet and GRU. As a result, our approach can greatly improve model training speed and web attack detection accuracy and recall.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF COMPUTING > ERICA 컴퓨터학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.