Application of Synthetic Data to the Problem of Anomaly Detection in the Field of Information Security
Main Article Content
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
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
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.