Can I read Model Uncertainty Based Annotation Error Fixing for Web Attack Detection on EtoBox?

Model Uncertainty Based Annotation Error Fixing for Web Attack Detection by Gong, Xinyu; Lu, Jialiang; Zhou, Yuefu; Qiu, Han; He, Ruan is a Computer Science article available to read on EtoBox.

What is Model Uncertainty Based Annotation Error Fixing for Web Attack Detection about?

Deep learning (DL) techniques have been widely used in web attack detection domain. With the stronger ability to fit data, DL models are also more sensitive to the training data, annotation errors can mislead the model training very easily. In our work, we propose model uncertainty to evaluate the prediction made by the DL based web attack model. Model uncertainty helps to find the annotation errors and also the misclassification caused by these errors. Experiments on two real web log datasets and a public benchmark dataset prove that our method can find more annotation errors than the traditional DL method. We also prove the efficiency of our detection model: with the aid of GPU acceleration, it is capable of tackling attacks on the fly. The development of the Internet brings increasing traffic on the web application side. The growing volume and variety of web traffic bring the researchers to the Big Data age [1-3] of web security. In the past decades, many researches have been conducted to apply Machine Learning (ML) algorithms [4,5] like decision tree and support vector machine in cyber attack detection. The training stage of these ML models is equivalent to let the model build

Who reads Model Uncertainty Based Annotation Error Fixing for Web Attack Detection?

Author

Gong, Xinyu; Lu, Jialiang; Zhou, Yuefu; Qiu, Han; He, Ruan

Publisher

Springer US; Springer-Verlag; Springer Verlag; Springer Science and Business Media LLC (ISSN 1939-8018)

Published

2020

Language

EN

Field

Computer Science (Physical Sciences)