Abstract
The ever-growing occurrence of computer security incidents calls for advanced intrusion detection techniques. A wide body of literature dealing with Intrusion Detection Systems (IDSes) is based on machine learning; many proposals rely on the use of autoencoders (AEs), due to their capability to analyze complex, high-dimensional and large-scale data. Most of the times, AEs are used as building blocks of much more complex detection architectures, possibly in combination with sophisticated feature selection techniques. This paper summarizes several years of work in this field, suggesting that “simpler is better” and that a carefully tuned and trained AE can be used in isolation, obtaining recognition results comparable with those attained by more complex designs. The best practices presented here, regarding dataset production and sanitization, AE set-up and training, threshold setting, possible use of simple feature selection techniques for performance improvement can be valuable for any practitioner willing to use autoencoders for intrusion detection purposes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
Attacks are taken from the USB-IDS-1 dataset.
References
Catillo, M., Del Vecchio, A., Ocone, L., Pecchia, A., Villano, U.: USB-IDS-1: a public multilayer dataset of labeled network flows for IDS evaluation. In: Proceedings International Conference on Dependable Systems and Networks Workshops (DSN-W), pp. 1–6. IEEE (2021)
Catillo, M., Pecchia, A., Villano, U.: AutoLog: anomaly detection by deep autoencoding of system logs. Expert Syst. Appl. 191, 116263 (2022)
Catillo, M., Rak, M., Villano, U.: Discovery of DoS attacks by the ZED-IDS anomaly detector. J. High Speed Netw. 25(4), 349–365 (2019)
Catillo, M., Del Vecchio, A., Pecchia, A., Villano, U.: Transferability of machine learning models learned from public intrusion detection datasets: the CICIDS2017 case study. Softw. Qual. J. (2022). https://doi.org/10.1007/s11219-022-09587-0
Catillo, M., Pecchia, A., Rak, M., Villano, U.: Demystifying the role of public intrusion datasets: a replication study of DoS network traffic data. Comput. Secur. 108, 102341 (2021)
Catillo, M., Rak, M., Villano, U.: 2L-ZED-IDS: a two-level anomaly detector for multiple attack classes. In: Barolli, L., Amato, F., Moscato, F., Enokido, T., Takizawa, M. (eds.) WAINA 2020. AISC, vol. 1150, pp. 687–696. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44038-1_63
Dina, A.S., Manivannan, D.: Intrusion detection based on machine learning techniques in computer networks. Internet Things 16, 100462 (2021)
Engelen, G., Rimmer, V., Joosen, W.: Troubleshooting an intrusion detection dataset: the CICIDS2017 case study. In: 2021 IEEE Security and Privacy Workshops (SPW), pp. 7–12. IEEE (2021)
Feng, S., Duarte, M.F.: Graph regularized autoencoder-based unsupervised feature selection. In: Proceedings International Conference on Signals, Systems, and Computers, pp. 55–59. IEEE (2018)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Jiang, J., Han, G., Liu, L., Shu, L., Guizani, M.: Outlier detection approaches based on machine learning in the Internet-of-Things. IEEE Wirel. Commun. 27(3), 53–59 (2020)
Khraisat, A., Gondal, I., Vamplew, P., Kamruzzaman, J.: Survey of intrusion detection systems: techniques, datasets and challenges. Cybersecurity 2(1), 1–22 (2019). https://doi.org/10.1186/s42400-019-0038-7
Kilincer, I., Ertam, F., Sengur, A.: Machine learning methods for cyber security intrusion detection: datasets and comparative study. Comput. Netw. 188, 107840 (2021)
Kramer, M.A.: Nonlinear principal component analysis using autoassociative neural networks. AIChE J. 37(2), 233–243 (1991)
Kunang, Y.N., Nurmaini, S., Stiawan, D., Zarkasi, A., Firdaus, Jasmir: Automatic features extraction using autoencoder in intrusion detection system. In: Proceedings International Conference on Electrical Engineering and Computer Science (ICECOS), pp. 219–224. IEEE (2018)
Kwon, D., Kim, H., Kim, J., Suh, S.C., Kim, I., Kim, K.J.: A survey of deep learning-based network anomaly detection. Clust. Comput. 22(1), 949–961 (2017). https://doi.org/10.1007/s10586-017-1117-8
Maciá-Fernández, G., Camacho, J., Magán-Carrión, R., García-Teodoro, P., Therón, R.: UGR’16: a new dataset for the evaluation of cyclostationarity-based network IDSs. Comput. Secur. 73, 411–424 (2017)
Maseer, Z.K., Yusof, R., Bahaman, N., Mostafa, S.A., Foozy, C.F.M.: Benchmarking of machine learning for anomaly based intrusion detection systems in the CICIDS2017 dataset. IEEE Access 9, 22351–22370 (2021)
Min, B., Yoo, J., Kim, S., Shin, D., Shin, D.: Network anomaly detection using memory-augmented deep autoencoder. IEEE Access 9, 104695–104706 (2021)
Mirsky, Y., Doitshman, T., Elovici, Y., Shabtai, A.: Kitsune: an ensemble of autoencoders for online network intrusion detection. In: Proceedings International Conference of Network and Distributed System Security Symposium (NDSS) (2018)
Moustafa, N., Slay, J.: UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: Proceedings International Conference Military Communications and Information Systems Conference, pp. 1–6. IEEE (2015)
Panigrahi, R., et al.: Performance assessment of supervised classifiers for designing intrusion detection systems: a comprehensive review and recommendations for future research. Mathematics 9(6), 690 (2021)
Ring, M., Wunderlich, S., Scheuring, D., Landes, D., Hotho, A.: A survey of network-based intrusion detection data sets. Comput. Secur. 86, 147–167 (2019)
Sharafaldin, I., Lashkari, A.H., Ghorbani., A.A.: Toward generating a new intrusion detection dataset and intrusion traffic characterization. In: Proceedings International Conference on Information Systems Security and Privacy, pp. 108–116. SciTePress (2018)
Taher, K.A., Mohammed Yasin Jisan, B., Rahman, M.M.: Network intrusion detection using supervised machine learning technique with feature selection. In: Proceedings International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST). IEEE (2019)
Thakur, S., Chakraborty, A., De, R., Kumar, N., Sarkar, R.: Intrusion detection in cyber-physical systems using a generic and domain specific deep autoencoder model. Comput. Electr. Eng. 91, 107044 (2021)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Wei-Chao, L., Shih-Wen, K., Chih-Fong, T.: CANN: an intrusion detection system based on combining cluster centers and nearest neighbors. Knowl. Based Syst. 78, 13–21 (2015)
XuKui, L., Wei, C., Qianru, Z., Lifa, W.: Building auto-encoder intrusion detection system based on random forest feature selection. Comput. Secur. 95, 101851 (2020)
Zhong, Y., et al.: HELAD: a novel network anomaly detection model based on heterogeneous ensemble learning. Comput. Netw. 169 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Catillo, M., Pecchia, A., Villano, U. (2022). Simpler Is Better: On the Use of Autoencoders for Intrusion Detection. In: Vallecillo, A., Visser, J., Pérez-Castillo, R. (eds) Quality of Information and Communications Technology. QUATIC 2022. Communications in Computer and Information Science, vol 1621. Springer, Cham. https://doi.org/10.1007/978-3-031-14179-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-14179-9_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-14178-2
Online ISBN: 978-3-031-14179-9
eBook Packages: Computer ScienceComputer Science (R0)