Ensemble of Deep Convolutional Learning Classifier System Based on Genetic Algorithm for Database Intrusion Detection

Seok-Jun Bu,Sung-Bae Cho,Han-Bit Kang

doi:10.3390/electronics11050745

Abstract

Methods of applying deep learning to database protection have increased over the years. To secure role-based access control (RBAC) by learning the mapping function between query features and roles, it is known that the convolutional neural networks combined with learning classifier systems (LCS) can reach formidable accuracy. However, current methods are focused on using a singular model architecture and fail to fully exploit features that other models are capable of utilizing. Different deep architectures, such as ResNet and Inception, can exploit different spatial correlations within the feature space. In this paper, we propose an ensemble of multiple models with different deep convolutional architectures to improve the overall coverage of features used in role classification. By combining models with heterogeneous topologies, the ensemble-LCS model shows significantly increased performance compared to previous single architecture LCS models and achieves better robustness in the case of training data imbalance.

Highlights

Well-known threats to relational databases can be classified into outsider attacks and insider attacks [4]
Paper, we we propose propose aa method method that that mitigates this shortcoming by using multiple model architectures in conjunctions, mitigates this shortcoming by using multiple model architectures in conjunctions, increasing increasing the the system’s system’s feature feature space space coverage
10‐fold cross‐validation in terms of 10 classification accuracy, Number of Population which is followed by quantitative comparison with the relevant deep learning models, Number of Elites including previous CN‐learning classifier systems (LCS) models

Summary

Introduction

Database security is a constantly changing field, with attackers searching and exploiting weak points in current defense measures and defenders that develop new methods to protect the database from newly discovered exploits and trying to fortify security measures to future threats [1]. Well-known threats to relational databases can be classified into outsider attacks and insider attacks [4]. Outsider attacks, such as SQL injections, can be relatively detected with traditional methods.

Methods

Results

Conclusion