Application of Synthetic Data to the Problem of Anomaly Detection in the Field of Information Security

Main Article Content

Artem Igorevich Gurianov

Abstract

Currently, synthetic data is highly relevant in machine learning. Modern synthetic data generation algorithms make it possible to generate data that is very similar in statistical properties to the original data. Synthetic data is used in practice in a wide range of tasks, including those related to data augmentation.


The author of the article proposes a data augmentation method that combines the approaches of increasing the sample size using synthetic data and synthetic anomaly generation. This method has been used to solve an information security problem of anomaly detection in server logs in order to detect attacks.


The model trained for the task shows high results. This demonstrates the effectiveness of using synthetic data to increase sample size and generate anomalies, as well as the ability to use these approaches together with high efficiency.

Article Details

References

1. Synthetic Data Generation Market by End-user, Type, and Geography – Analysis and Forecast // Technavio. 2023. URL: https://www.technavio.com/report/synthetic-data-generation-market-analysis (дата обращения 04.02.2024)
2. Assefa S., Dervovic D., Mahfouz M., Balch T., Reddy P., Veloso M. Generating Synthetic Data in Finance: Opportunities, Challenges and Pitfalls // Proceedings of the First ACM International Conference on AI in Finance. 2020. https://doi.org/10.1145/3383455.3422554
3. James S., Harbron C., Branson J., Sundler M. Synthetic data use: exploring use cases to optimise data utility // Discover Artificial Intelligence. 2021. V. 1. https://doi.org/10.1007/s44163-021-00016-y
4. Jordon J., Szpruch L. et al. Synthetic Data – what, why and how? // ArXiv. 2022. https://doi.org/10.48550/arXiv.2205.03257
5. Хафизов А.В., Григорьев М.В. Генерирование синтетических пористых изображений для аугментации данных с целью тренировки алгоритмов машинного обучения // Сенсорные системы. 2021. Т. 35, № 4. С. 340–347. https://doi.org/10.31857/S023500922104003X
6. Heine J., Fowler E.E.E., Berglund A., Schell M.J., Eschrich S. Techniques to produce and evaluate realistic multivariate synthetic data // Scientific Reports. 2023. V. 13. https://doi.org/10.1038/s41598-023-38832-0
7. Vicente C., Muzo D., Jiménez I., Fabelo H., Gram I.T., Løchen M., Granja C., Ruiz C. Evaluation of Synthetic Categorical Data Generation Techniques for Predicting Cardiovascular Diseases and Post-Hoc Interpretability of the Risk Factors // Applied Sciences. 2023. Vol. 13(7). https://doi.org/10.3390/app13074119
8. Wang Z., Wang H. Global Data Distribution Weighted Synthetic Oversampling Technique for Imbalanced Learning // IEEE Access. 2021. V. 9. P. 44770–44783. https://doi.org/10.1109/ACCESS.2021.3067060
9. Astrid M., Zaheer M., Lee S. Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection // 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). 2021. P. 207–214. https://doi.org/10.1109/ICCVW54120.2021.00028
10. Luo M., Wang K., Cai Z., Liu A., Li Y., Cheang C.F. Using Imbalanced Triangle Synthetic Data for Machine Learning Anomaly Detection // Computers, Materials & Continua. 2019. V. 58(1). P. 15–26. https://doi.org/10.32604/cmc.2019.03708
11. Salem M., Taheri S., Yuan J.S. Anomaly Generation Using Generative Adversarial Networks in Host-Based Intrusion Detection // 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference. 2018. P. 683–687. https://doi.org/10.1109/UEMCON.2018.8796769
12. Smolyakov D., Sviridenko N., Ishimtsev V., Burikov E., Burnaev E. Learning Ensembles of Anomaly Detectors on Synthetic Data // International Symposium on Neural Networks. 2019. https://doi.org/10.1007/978-3-030-22808-8_30
13. Емельянов С.О., Иванова А.А., Швец Е.А., Николаев Д.П. Методы аугментации обучающих выборок в задачах классификации изображений // Сенсорные системы. 2018. Т. 32, № 3. С. 236–245.
https://doi.org/10.1134/S0235009218030058
14. Ping H., Stoyanovich J., Howe B. DataSynthesizer: Privacy-Preserving Synthetic Datasets // Proceedings of the 29th International Conference on Scientific and Statistical Database Management. 2017. P. 1–5. https://doi.org/10.1145/3085504.3091117
15. DataResponsibly / DataSynthesizer // GitHub. URL: https://github.com/DataResponsibly/DataSynthesizer (дата обращения 12.01.2024)
16. Han S., Hu X., Huang H., Jiang M., Zhao Y. ADBench: Anomaly Detection Benchmark // Neural Information Processing Systems (NeurIPS). 2022.
17. Minqi824 / ADBench // GitHub. URL: https://github.com/Minqi824/ADBench (дата обращения 23.01.2024)
18. Liu F.T., Ting K.M., Zhou Z. Isolation Forest // Eighth IEEE International Conference on Data Mining. 2008. P. 413–422. https://doi.org/10.1109/ICDM.2008.17
19. Snoek J., Larochelle H., Adams R.P. Practical Bayesian Optimization of Machine Learning Algorithms // Advances in Neural Information Processing Systems 25. 2012.
20. Yang L., Shami A. On hyperparameter optimization of machine learning algorithms: Theory and practice // Neurocomputing. 2020. V. 415. P. 295–316. https://doi.org/10.1016/j.neucom.2020.07.061