A Model for Intrusion Detection and Prevention in a Database System Using Deep Learning
Keywords:
Intrusion Detection, Anomaly Detection, Response Policy, Deep Learning, DatabaseAbstract
With emerging and improved technologies, attacks on database systems and network have also increased. Among the top 10 security weaknesses mentioned, SQL injection and cross-site scripting attacks are the two most significant that cause anomalies in Database Systems. Although these datasets in the database may contain outliers which are typically abnormalities, and therefore accurate classification is necessary in order to prevent false alarms and identify these anomalies. This research created a deep-learning model for the detection and prevention of anomalies in database systems in response to the exponential growth of anomalies (SQL injection and Cross Site Scripting) on web applications. This approach was chosen over the conventional machine learning approach because it can handle large data sets and produce results that are more accurate. Moreover, an experiment was conducted using the Long Short-Term Memory algorithm to demonstrate the effectiveness of the proposed system. The proposed system was then compared to an already existing system based on performance and the result showed that it outperformed, having an accuracy of 99% over 91.5% of the already existing system, which is deemed satisfactory.
References
Grushka CH, Ofer B, Dymshits M, Rokach L, Shapira B. Sampling high throughput data for anomaly detection of data-base activity. Proceedings of the 11th Pre-ICIS Workshop on Information Security and Privacy. 2017; 1: 1–5.
Srinivas VB. A Review of Security Mechanisms for Detection of Malicious Transactions in Database. Glob J Comput Sci Technol. 2014 May 15; 14(E8): 1–6.
Rivnay J, Wang H, Fenno L, Deisseroth K, Malliaras GG. Next-generation probes, particles, and proteins for neural interfacing. Sci Adv. 2017 Jun 9; 3(6): e1601649.
Ngadi M, Al-Dhaqm R, Mohammed A. Detection and prevention of malicious activities on RDBMS relational database management systems. Int J Sci Eng Res. 2012; 3(9): 1–10.
Aldallal A, Alisa F. Effective intrusion detection system to secure data in cloud using machine learning. Symmetry. 2021 Dec 3; 13(12): 2306.
Bu SJ, Kang HB, Cho SB. Ensemble of Deep Convolutional Learning Classifier System Based on Genetic Algorithm for Database Intrusion Detection. Electronics. 2022 Feb 28; 11(5): 745.
Rao UP, Singh NK. Weighted Role Based Data Dependency Approach for Intrusion Detection in Database. Int J Netw Secur. 2017 May 1; 19(3): 358–70.
Coronel C, Morris S. Database systems: Design, implementation, & management. Boston, USA: Cengage Learning; Jan 2016.
Althebyan Q. Design and analysis of knowledge-based centric insider threat models. Thesis. USA: University of Arkansas; 2008.
Nguyen N, Reiher P, Kuenning GH. Detecting insider threats by monitoring system call activity. In IEEE Systems, Man and Cybernetics Society Information Assurance Workshop, 2003. 2003 Jun 18; 45–52.
Theoharidou M, Kokolakis S. The insider threat to information systems and the effectiveness of ISO17799. Comput Secur. 2005; 24(6): 472–484.
Shatnawi N, Althebyan Q, Mardini W. Detection of insiders misuse in database systems. Proceedings of the International Multi-Conference of Engineers and Computer Scientists 2011. Vol I. IMECS 2011. 2011, March 16–18.
Anuar NB, Sallehudin H, Gani A, Zakaria O. Identifying false alarm for network intrusion detection system using hybrid data mining and decision tree. Malaysian J Comput Sci. 2008 Dec 1; 21(2): 101–115.
Farnaaz N, Jabbar MA. Random forest modeling for network intrusion detection system. Procedia Comput Sci. 2016 Jan 1; 89: 213–7.
Yang Y, Zheng K, Wu C, Yang Y. Improving the classification effectiveness of intrusion detection by using improved conditional variational autoencoder and deep neural network. Sensors. 2019 Jun 2; 19(11): 2528.
Vieira M, Madeira H. Detection of malicious transactions in DBMS. In IEEE 11th Pacific Rim International Symposium on Dependable Computing (PRDC'05). 2005 Dec 12.
Vavilis S, Egner A, Petković M, Zannone N. An anomaly analysis framework for database systems. Comput Secur. 2015 Sep 1; 53: 156–173.
Binbusayyis A, Vaiyapuri T. Identifying and benchmarking key features for cyber intrusion detection: An ensemble approach. IEEE Access. 2019 Jul 17; 7: 106495–513.
Subudhi S, Panigrahi S. Application of OPTICS and ensemble learning for database intrusion detection. J King Saud Univ-Comput Inf Sci. 2022 Mar 1; 34(3): 972–981.
Singh I, Jindal R. Expectation maximization clustering and sequential pattern mining based approach for detecting intrusive transactions in databases. Multimed Tools Appl. 2021 Jul; 80(18): 27649–81.
