Abstract
The increasing digitization and interconnection of Industrial Control Systems (ICS) to the Internet make them an attractive target for sophisticated attacks performed by experienced adversaries with high motivation and resources. As ICS incorporate decades-old devices and communication infrastructure, new generation embedded devices with computing capabilities and Ethernet-based communication protocols, the integration of proactive security protection methods is very challenging. Thus, a major line of research focuses on the development of reactive security solutions in the form of industrial intrusion detection systems (IIDS) aiming to detect anomalies in otherwise predictable “normal” ICS behavior. A crucial requirement for the assessment of the actual, real-world performance of these methods and their fair comparison is the existence of a representative dataset. Although the number of public ICS datasets increases gradually, it remains unclear to which extent these datasets can be considered as representative.
In this work, we identify key properties a given ICS dataset should own to be designated as representative based on typical IIDS evaluation scenarios. Our systematization of knowledge highlights that these properties are only partially represented in the existing public ICS datasets, which makes them unrepresentative, and shed light on the need for new datasets for IIDS evaluation. We further make a step into the direction of generating a representative dataset and present our ongoing work on the construction of a Hardware in the Loop tesbed of a real water distribution system. Our testbed replicates the operation of a real German medium-sized water supplier and allows for the collection of three different types of data sources, i.e., physical information, network data, and system logs. Our initial dataset contains more than 20 attacks targeting both at the distortion of the underlying physical process and at network- and system-based cyber attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The first dataset contains two labels indicating attack and no attack. The second dataset contains three labels indicating attack, no attack, or normal failure. The third dataset includes additionally a separate label for each attack.
- 2.
We omit the discussion of another group of gas pipeline and water storage tank datasets by Morris et al. as these datasets contain unintended patterns and, thus, are broken [20].
- 3.
In our work, we categorize these attacks as getting-access attacks.
- 4.
During the preparation of this work, the website [1], which the dataset is published on, was not reachable, which hindered the investigation of this dataset.
References
Electra dataset: Anomaly detection ICS dataset. https://perception.inf.um.es/ICS-datasets/
HAI (HIL-based Augmented ICS) Security Dataset. https://github.com/icsdataset/hai
Siemens communications overview. https://snap7.sourceforge.net/siemens_comm.html
Gómez, Á.L.P., et al.: On the generation of anomaly detection datasets in industrial control systems. IEEE Access 7 (2019)
Erba, A., et al.: Constrained concealment attacks against reconstruction-based anomaly detectors in industrial control systems. In: Annual Computer Security Applications Conference, ACSAC. ACM (2020)
Ahmed, C.M., et al.: WADI: a water distribution testbed for research in the design of secure cyber physical systems. In: 3rd International Workshop on Cyber-Physical Systems for Smart Water Networks, CySWATER. ACM (2017)
Myers, D., et al.: Anomaly detection for industrial control systems using process mining. Comput. Secur. 78 (2018)
Zizzo, G., et al.: Adversarial attacks on time-series intrusion detection for industrial control systems. In: 19th International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom. IEEE (2020)
Shin, H.K., et al.: Implementation of programmable CPS testbed for anomaly detection. In: 12th Workshop on Cyber Security Experimentation and Test, CSET. USENIX Association (2019)
Shin, H.K., et al.: HAI 1.0: HIL-based augmented ICS security dataset. In: 13th Workshop on Cyber Security Experimentation and Test, CSET. USENIX Association (2020)
Shin, H.K., et al.: Two ICS security datasets and anomaly detection contest on the HIL-based augmented ICS testbed. In: 14th Workshop on Cyber Security Experimentation and Test., CSET. ACM (2021)
Giraldo, J., et al.: A survey of physics-based attack detection in cyber-physical systems. ACM Comput. Surv. 51(4) (2018)
Suaboot, J., et al.: A taxonomy of supervised learning for IDSs in SCADA environments. ACM Comput. Surv. 53(2) (2020)
Goh, J., Adepu, S., Junejo, K.N., Mathur, A.: A dataset to support research in the design of secure water treatment systems. In: Havarneanu, G., Setola, R., Nassopoulos, H., Wolthusen, S. (eds.) CRITIS 2016. LNCS, vol. 10242, pp. 88–99. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71368-7_8
Conti, M., et al.: A survey on industrial control system testbeds and datasets for security research. IEEE Commun. Surv. Tutor. 23(4) (2021)
Taormina, R., et al.: Battle of the attack detection algorithms: disclosing cyber attacks on water distribution networks. J. Water Resour. Plan. Manag. 144(8) (2018)
Taormina, R., et al.: A toolbox for assessing the impacts of cyber-physical attacks on water distribution systems. Environ. Model. Softw. 112 (2019)
Pan, S., et al.: Developing a hybrid intrusion detection system using data mining for power systems. IEEE Trans. Smart Grid 6(6) (2015)
Adepu, S., Kandasamy, N.K., Mathur, A.: EPIC: an electric power testbed for research and training in cyber physical systems security. In: Katsikas, S.K., et al. (eds.) SECPRE/CyberICPS 2018. LNCS, vol. 11387, pp. 37–52. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12786-2_3
Adhikari, U., et al.: Industrial Control System (ICS) Cyber Attack Datasets (2022). https://sites.google.com/a/uah.edu/tommy-morris-uah/ics-data-sets
ATT &CK, M.: ICS Matrix. https://attack.mitre.org/matrices/ics/
Choi, S., Yun, J.-H., Kim, S.-K.: A comparison of ICS datasets for security research based on attack paths. In: Luiijf, E., Žutautaitė, I., Hämmerli, B.M. (eds.) CRITIS 2018. LNCS, vol. 11260, pp. 154–166. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-05849-4_12
Frazão, I., Abreu, P.H., Cruz, T., Araújo, H., Simões, P.: Denial of service attacks: detecting the frailties of machine learning algorithms in the classification process. In: Luiijf, E., Žutautaitė, I., Hämmerli, B.M. (eds.) CRITIS 2018. LNCS, vol. 11260, pp. 230–235. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-05849-4_19
Hink, R.C.B., Goseva-Popstojanova, K.: Characterization of cyberattacks aimed at integrated industrial control and enterprise systems: a case study. In: 17th International Symposium on High Assurance Systems Engineering, HASE. IEEE (2016)
iTrust: Secure Water Treatment (SWaT) Testbed (2022). https://itrust.sutd.edu.sg/testbeds/secure-water-treatment-swat/
Kravchik, M., Shabtai, A.: Efficient Cyber Attacks Detection in Industrial Control Systems Using Lightweight Neural Networks and PCA (2019)
Kus, D., et al.: A false sense of security? Revisiting the state of machine learning-based industrial intrusion detection. In: 8th Workshop on Cyber-Physical System Security, CPSS. ACM (2022)
Lemay, A., Fernandez, J.M.: Providing SCADA network data sets for intrusion detection research. In: 9th Workshop on Cyber Security Experimentation and Test, CSET. USENIX Association (2016)
Lounge, G.: Capture files from 4SICS Geek Lounge. https://www.netresec.com/?page=PCAP4SICS
Mehner, S., Schuster, F., Hohlfeld, O.: Lights on power plant control networks. In: Hohlfeld, O., Moura, G., Pelsser, C. (eds.) PAM 2022. LNCS, vol. 13210, pp. 470–484. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-98785-5_21
Microsoft: PowerShell Documentation. https://docs.microsoft.com/en-us/powershell/
Ndonda, G.K., Sadre, R.: A Public Network Trace of a Control and Automation System. https://arxiv.org/pdf/1908.02118.pdf
Peterson, D., Wightman, R.: S4x15 ICS Village PCAP Files. https://www.netresec.com/?page=DigitalBond_S4
(PI), P.P.I.: Profibus
Pliatsios, D., et al.: A survey on SCADA systems: secure protocols, incidents, threats and tactics. IEEE Commun. Surv. Tutor. 22(3) (2020)
Rodofile, N.R.: DNP3 Cyber-attack datasets. https://github.com/qut-infosec/2017QUT_DNP3
Rodofile, N.R.: SCADA network attack datasets and process logs. https://github.com/qut-infosec/2017QUT_S7comm
Rodofile, N.R.: Generating attacks and labelling attack datasets for industrial control intrusion detection systems. Ph.D. thesis, Queensland University of Technology (2013)
Siemens: S7-400 Automation System, CPU Specifications (2009). https://cache.industry.siemens.com/dl/files/550/23904550/att_98310/v1/CPU_data_en_en-US.pdf?download=true
Siemens: SIMULATIONUnit Manual (2022). https://cache.industry.siemens.com/dl/files/344/109475344/att_926827/v1/HelpEN.pdf
Siemens: Software for the visualization of the future (2022). https://new.siemens.com/global/en/products/automation/simatic-hmi/wincc-unified/software.html
Turrin, F., et al.: A statistical analysis framework for ICS process datasets. In: Joint Workshop on CPS &IoT Security and Privacy. ACM (2020)
Zemanek, S., et al.: PowerDuck: a GOOSE data set of cyberattacks in substations. In: 15th Workshop on Cyber Security Experimentation and Test, CSET. ACM (2022)
Acknowledgments
This work has been funded by the German Federal Ministry of Education and Research (BMBF) under the project KISS_KI Simple & Scalable and the EU and state Brandenburg EFRE StaF project INSPIRE.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mitseva, A., Thierse, P., Hoffmann, H., Er, D., Panchenko, A. (2023). Challenges and Pitfalls in Generating Representative ICS Datasets in Cyber Security Research. In: Katsikas, S., et al. Computer Security. ESORICS 2022 International Workshops. ESORICS 2022. Lecture Notes in Computer Science, vol 13785. Springer, Cham. https://doi.org/10.1007/978-3-031-25460-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-25460-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25459-8
Online ISBN: 978-3-031-25460-4
eBook Packages: Computer ScienceComputer Science (R0)