The requirements for the security of the network communication in critical infrastructures have been more focused on the availability of the data rather than the integrity and the confidentiality. The availability of communication in IEC 61850 substations can be hindered by Generic Object Oriented Substation Event (GOOSE) poisoning attacks that might result in threats such as Denial of Service (DoS) or flooding attacks. In order to accurately detect similar attacks, a novel method for the Early Detection of Attacks for GOOSE Network Traffic (EDA4GNeT) is developed in the present work. The EDA4GNeT method considers the dynamic behavior of network traffic in electrical substations. A mathematical modeling of GOOSE network traffic is adopted for the anomaly detection based on statistical hypothesis testing. The developed mathematical model of the communication traffic can also support the management of the network architecture in IEC 61850 substations based on appropriate performance studies. To test the novel anomaly detection method and compare the obtained results with related works found in the literature, a simulation of a DoS attack against a ${66/11}{\mathrm{ kV}}$ substation with several experiments is used as a case study.
Integration of Information and Communication Technology (ICT) in modern smart grids (SGs) offers many advantages including the use of renewables and an effective way to protect, control and monitor the energy transmission and distribution. To reach an optimal operation of future energy systems, availability, integrity and confidentiality of data should be guaranteed. Research on the cyber-physical security of electrical substations based on IEC 61850 is still at an early stage. In the present work, we first model the network traffic data in electrical substations, then, we present a statistical Anomaly Detection (AD) method to detect Denial of Service (DoS) attacks against the Generic Object Oriented Substation Event (GOOSE) network communication. According to interpretations on the self-similarity and the Long-Range Dependency (LRD) of the data, an Auto-Regressive Fractionally Integrated Moving Average (ARFIMA) model was shown to describe well the GOOSE communication in the substation process network. Based on this ARFIMA-model and in view of cyber-physical security, an effective model-based AD method is developed and analyzed. Two variants of the statistical AD considering statistical hypothesis testing based on the Generalized Likelihood Ratio Test (GLRT) and the cumulative sum (CUSUM) are presented to detect flooding attacks that might affect the availability of the data. Our work presents a novel AD method, with two different variants, tailored to the specific features of the GOOSE traffic in IEC 61850 substations. The statistical AD is capable of detecting anomalies at unknown change times under the realistic assumption of unknown model parameters. The performance of both variants of the AD method is validated and assessed using data collected from a simulation case study. We perform several Monte-Carlo simulations under different noise variances. The detection delay is provided for each detector and it represents the number of discrete time samples after which an anomaly is detected. In fact, our statistical AD method with both variants (CUSUM and GLRT) has around half the false positive rate and a smaller detection delay when compared with two of the closest works found in the literature. Our AD approach based on the GLRT detector has the smallest false positive rate among all considered approaches. Whereas, our AD approach based on the CUSUM test has the lowest false negative rate thus the best detection rate. Depending on the requirements as well as the costs of false alarms or missed anomalies, both variants of our statistical detection method can be used and are further analyzed using composite detection metrics.
IT vulnerabilities, cyber threats, and resulting risks significantly impact the stability of current and future power grids. The results of a Risk Assessment process contribute to a better understanding of the causes and nature of the associated risks. The risks assessed by experts are available in both numerical and linguistic representations – this makes it beneficial to include a combination of linguistic and numerical analyses. In this paper, we propose a new Hybrid Risk Assessment method based on fuzzy logic, leading to more precise results. The presented approach specifies the variables and membership functions of fuzzy logic with reference to Smart Grids. For this propose, a case study with five risk events in a small-scale Smart Grid is carried out as an example. The results can then support decision-makers in ensuring grid stability.
Learning-based components applied to a plethora of use cases within smart grids are already a reality. These methods will undoubtedly play a key role in future energy systems. This paper addresses challenges in the field of adversarial attacks against learning-based models in the context of smart grids. We identify unexplored areas and potential improvements in current methodologies by categorizing attacks, and assessing their ability to be reproduced. Our survey showed a noticeable resistance to distributing experimental code. Additionally, we propose the integration of explainable artificial intelligence techniques into adversarial models. We carry out an initial experiment to showcase the possible effects of this integration, offering fresh perspectives on the behavior and vulnerabilities of learning-based models within smart grids. Our initial findings provide a basis for further investigation into adversarial attacks, with a special focus on use cases that affect electrical substation security. Finally, we outline the next steps of our research in this critical area.
Artificial intelligence techniques play a significant role in the cybersecurity of smart grids (SGs). Machine learning (ML) algorithms can successfully differentiate between normal behaviour and attacks, even if the anomalies are a by-product of malicious techniques never seen before. However, malicious actors successfully evade ML-based intrusion detection systems (IDSs) with attacks that mimic normal operation. In the present paper, we proactively test ML-based intrusion detection algorithms against adversarial scenarios for a better understanding of malicious capabilities. We start with the implementation of attacks (reconnaissance, data modification on the fly, and denial of service against Modbus TCP) in our testbed at KASTEL Security Lab Energy. Then, we develop a prototype ML-based IDS that monitors Modbus TCP traffic. We explicitly discuss the feasibility of evasion attacks in the problem space of Modbus TCP. Finally, we report our findings and discuss challenges from the attacker’s point of view. Additionally, considering the scarcity of available datasets for effective evaluation of IDS approaches, we release our dataset which includes Modbus TCP network traffic.