Machine learning based anomaly detection method for SQL
In this paper, an anomaly detection method for SQL is proposed. The method is based on the clasterization and recurrent neural networks for legitimate SQL-queries. The main idea is to teach neural network to detect non-typical SQL-queries for the server including queries independent from known instances of successful attacks.
Download file
Counter downloads: 223
Keywords
машинное обучение, обнаружение аномалий, SQL-инъекции, кластеризация, рекуррентные нейронные сети, machine learning, anomaly detection, SQL-injections, Rasterization, recurrent neural networkAuthors
| Name | Organization | |
| Murzina A. I. | Tomsk State University | murzina93@gmail.com |
References
OWASP Top 10 Application Security Risks - 2017. https://www.owasp.org/index.php/Top_ 10_2017-Top_10
Halfond W. G. J., ViegasJ., and Orso A. A classification of SQL injection attacks and countermeasures // Proc. ISSSE 2006, Washington, USA, Mar. 2006. https://pdfs. semanticscholar.org/81a5/02b52485e52713ccab6d260f15871c2acdcb.pdf
Rawat R. and Shrivastav S. K. SQL injection attack detection using SVM // Intern. J. Comput. Appl. 2012. V. 42. No. 13. P. 1-4.
Buehrer G. T., Weide B. W., and Sivilotti P. A. G. Using parse tree validation to prevent SQL injection attacks // Proc. SEM'05. N.Y.: ACM, 2005. P. 106-113.
Cheng Y. Mean shift, mode seeking, and clustering // IEEE Trans. Pattern Analysis Machine Intelligence. 1995. V. 17. Iss.8. P. 790-799.
Schmidhuber J. and Hochreiter S. Long short-term memory // Neural Computation. 1997. No. 9. P. 1735-1780.
