A Hybrid System of Deep Learning and Learning Classifier System for Database Intrusion Detection

Bu, Seok-Jun; Cho, Sung Bae

doi:10.1007/978-3-319-59650-1_52

Cited by 14 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Choi et al [18] combined evolutionary reinforcement learning to optimize the learning process of CNNs, attempting to find the ideal learning rate for each training input using the evolutionary process. Bu et al [19] combined the CNN model with a Learning Classifier System (CN-LCS), allowing the model to learn which input features to focus on to improve model accuracy. Kim et al [20] used Particle Swarm Optimization to discover improved model topologies.…”

Section: Related Workmentioning

confidence: 99%

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

Kang

Cho

2022

Electronics

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Kang

Cho

2022

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, Bu et al [201], proposed CN-LCS, an IDS approach for a relational database management system that uses CNN and LCS or Learning Classifier System. This scheme can classify sparse and high-dimensional feature vectors of database queries with convolution-pooling operations and GA-based feature selection.…”

Section: F Cnn-based Schemesmentioning

confidence: 99%

Deep Learning-Based Intrusion Detection Systems: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

Nowadays, the ever-increasing complication and severity of security attacks on computer networks have inspired security researchers to incorporate different machine learning methods to protect the organizations' data and reputation. Deep learning is one of the exciting techniques which recently are vastly employed by the IDS or intrusion detection systems to increase their performance in securing the computer networks and hosts. This survey article focuses on the deep learning-based intrusion detection schemes and puts forward an in-depth survey and classification of these schemes. It first presents the primary background concepts about IDS architecture and various deep learning techniques. It then classifies these schemes according to the type of deep learning methods utilized in each of them. It describes how deep learning networks are utilized in the intrusion detection process to recognize intrusions accurately. Finally, a complete analysis of the investigated IDS frameworks is provided, and concluding remarks and future directions are highlighted.INDEX TERMS Intrusion detection, auto-encoder, recurrent neural network, Boltzmann machine, CNN.

show abstract

“…Fase pembelajaran data mining dan komponen deteksi preprocessor transaksi berbahaya dan pendeteksi tugas pengguna berbahaya memiliki tingkat positif sejati lebih tinggi dan akurasi sistem yang tinggi ketika batas kepercayaan dan dukungan ditetapkan ke nilai yang diinginkan [10]. Metode Convolutional Neural-Learning Classifier System menjadi model terbaik dengan tingkat akurasi tertinggi sebesar 94,64% dan matriks kebingungan klasifikasi mencapai akurasi pengujian 93,36% [11]. Penelitian menggabungkan algoritma Naïve Bayes dengan Teknik korelasi pada atribut memiliki tingkat akurasi yang lebih besar dengan tanpa Teknik korelasi dengan selisih 3,6% [12].…”

Section: Pendahuluanunclassified

Deteksi Intrusi Pada Basis Data Menggunakan Random Forest

Putri

Zulianto

Suwarningsih

2021

JICT

View full text Add to dashboard Cite

More services have been made online in recent years, more and more data is being stored virtually. This important and confidential data becomes an easy target for criminals in the era of digitalization. Database security becomes very necessary to keep data safe. Attacks can come from outside or from within, attacks caused by insiders are the second biggest threat after hacking. Conventional security has not been able to detect anomalies from internal users. This can be anticipated using an intrusion detection mechanism. This mechanism has previously been applied to networks and hosts. However, some actions that are harmful to the database are not necessarily harmful to the network and hosts so that intrusion detection on the database becomes extra security to defend the database from intruders. This system uses the Random Forest algorithm which includes supervised learning to detect anomalous transactions. The dataset used is a transaction log containing 773 records and 9 attributes. Anomalies are determined based on the threshold value of 3 attributes, namely operation, object and field name. The test uses 6 different trees, 10, 20, 40, 60, 80 and 100. The results of the test on 762 records and 5 attributes used, the Random Forest algorithm has the highest accuracy value on the number of trees 80 and 100 which have a test time difference of 0 .03 seconds. In the dataset used, the optimum number of trees is found at number 80 with an accuracy value of 99.56% and an execution time of 0.13183 seconds.

show abstract

A Hybrid System of Deep Learning and Learning Classifier System for Database Intrusion Detection

Cited by 14 publications

References 20 publications

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

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

Deep Learning-Based Intrusion Detection Systems: A Systematic Review

Deteksi Intrusi Pada Basis Data Menggunakan Random Forest

Contact Info

Product

Resources

About