Incidents Information Sharing Platform for Distributed Attack Detection

Fotiadou, K., Velivassaki, T. H., Voulkidis, A., Railis, K., Trakadas, P., & Zahariadis, T.
Intrusion detection plays a critical role in cyber-security domain since malicious attacks cause irreparable damages to cyber-systems. In this work, we propose the I2SP prototype, which is a novel Information Sharing Platform, able to gather, pre-process, model, and distribute network-traffic information. Within the I2SP prototype we build several challenging deep feature learning models for network-traffic intrusion detection. The learnt representations will be utilized for classifying each new network measurement into its corresponding threat level. We evaluate our prototype’s performance by conducting case studies using cyber-security data extracted from the Malware Information Sharing Platform (MISP)-API. To the best of our knowledge, we are the first that combine the MISP-API in order to construct an information sharing mechanism that supports multiple novel deep feature learning architectures for intrusion detection. Experimental results justify that the proposed deep feature learning techniques are able to predict accurately MISP threat-levels.

A Stochastic Assessment of Attacks based on Continuous-Time Markov Chains

Abhinav Sadu; Marija Stevic; Nikolaus Wirtz; Antonello Monti
With the increasing interdependence of critical infrastructures, the probability of a specific infrastructure to experience a complex cyber-physical attack is increasing. Thus it is important to analyze the risk of an attack and the dynamics of its propagation in order to design and deploy appropriate countermeasures. The attack trees, commonly adopted to this aim, have inherent shortcomings in representing interdependent, concurrent and sequential attacks. To overcome this, the work presented here proposes a stochastic methodology using Petri Nets and Continuous Time Markov Chain (CTMC) to analyze the attacks, considering the individual attack occurrence probabilities and their stochastic propagation times. A procedure to convert a basic attack tree into an equivalent CTMC is presented. The proposed method is applied in a case study to calculate the different attack propagation characteristics. The characteristics are namely, the probability of reaching the root node & sub attack nodes, the mean time to reach the root node and the mean time spent in the sub attack nodes before reaching the root node. Additionally, the method quantifies the effectiveness of specific defenses in reducing the attack risk considering the efficiency of individual defenses.

A Flexible Framework to Investigate Cascading in Interdependent Networks of Power Systems

Nikolaus Wirtz; Antonello Monti
This paper introduces a flexible framework to analyze cascading effects in the interdependent power and information and communications technology (ICT) networks that that comprise a power system. This framework supports integration of interdependencies between the power grid and various ICT networks, but also of domain-specific intra-dependencies of these different subsystems. The framework is applied to model a simple example system, where three failure scenarios are defined and simulated to showcase the applicability of the framework for the investigation of cascading effects.

Proactive Critical Energy Infrastructure Protection via Deep Feature Learning. Energies, 13 (10), 2622.

Fotiadou, K., Velivassaki, T. H., Voulkidis, A., Skias, D., De Santis, C., & Zahariadis, T. (2020).
Autonomous fault detection plays a major role in the Critical Energy Infrastructure (CEI) domain, since sensor faults cause irreparable damage and lead to incorrect results on the condition monitoring of Cyber-Physical (CP) systems. This paper focuses on the challenging application of wind turbine (WT) monitoring. Specifically, we propose the two challenging architectures based on learning deep features, namely—Long Short Term Memory-Stacked Autoencoders (LSTM-SAE), and Convolutional Neural Network (CNN-SAE), for semi-supervised fault detection in wind CPs. The internal learnt features will facilitate the classification task by assigning each upcoming measurement into its corresponding faulty/normal operation status. To illustrate the quality of our schemes, their performance is evaluated against real-world’s wind turbine data. From the experimental section we are able to validate that both LSTM-SAE and CNN-SAE schemes provide high classification scores, indicating the high detection rate of the fault level of the wind turbines. Additionally, slight modification on our architectures are able to be applied on different fault/anomaly detection categories on variant Cyber-Physical systems.

This project has received funding from the European Union’s Horizon 2020 research and Innovation programme under grant agreement N°832989. All information on this website reflects only the authors' view. The Agency and the Commission are not responsible for any use that may be made of the information this website contains.

Sign up to our newsletter