Communication Networks

The communication networks group works on the following topics:

Network Security

The protection of communication networks against new and unexpected attacks remains a challenging task. Attacks become more sophisticated. New vulnerabilities emerge every day. Proactive solutions often fail if new attack strategies are used or undetected vulnerabilities are exploited. Therefore, network supervision methods are essential to establish situational awareness in communication networks. They help to detect anomalies in communication patterns and provide the first step for the detection of new attack types.

The communication networks group works on network supervision and network protection methods, anomaly detection techniques and mitigation strategies.

Network Security Laboratory

Data Analysis and Network Traffic

Secure Communication
in Cyber-Physical Systems

Cyber‐physical systems (CPS) interconnect real world physical systems with computational components in cyberspace. Cyber‐physical systems provide the basis for many critical infrastructures (such as smart power grids) and are therefore tempting targets for all kinds of attackers. As a consequence, communication networks for cyber‐physical systems have high security demands. Interfering with supervision and control functions in cyberspace can influence real world physical systems, which can lead to the damage of physical devices, malfunction of critical processes and endangerment of human lives.

The Communication Networks group works on methods to protect and supervise communication networks for Cyber-Physical Systems. The group focuses on methods for smart grid environments and on IPv4 and IPv6 based communication.

Links to related sites

Business Analytics, Big Data, Data Mining and Data Science: KDnuggests

An online pattern collection for network steganography (network covert channels): Network Information Hiding Patterns

Center for Applied Internet Data Analysis: CAIDA

Research Topics

The communication networks group is currently active in the following research areas and projects:

Anomaly Detection and Traffic Analysis

Mountain visualization is a way to display clustering solutions for some traffic analysis cases
Mountain visualization is a possible way to display clustering solutions for some traffic analysis cases

The research is faced from two different perspectives: On one hand, we analyze traffic with the purpose of solving present problems related to the use of network communications as well as improving their current performance. A deep knowledge in statistics, machine learning and data mining tools is a mandatory requirement to dig into the entrails of real communications and infer what is happening there. On the other hand, traffic communications are deployed as high-complexity scenarios which challenge the current state of the art of analysis methodologies and, therefore, contribute to their improvement and a better understanding of their application. The topics covered by our research include:
Traffic Analysis: Data Preprocessing and Transformation, Multi-variate Analysis, Data and Meta-Data Visualization, Outlier Detection and Analysis, and Pattern Recognition.
Machine Learning: Dimensionality Reduction, Feature Selection, Proximity Measures and Similarity Metrics, Classification Criteria, Clustering Comparison, Validation Techniques, Design and Implementation of Test-beds.

Network Security Laboratory

Data Analysis and Network Traffic

Network Measurements

The communication networks group works on active and passive measurements methods for quality assessment and network security. The research focus is on efficient passive network supervision methods as well as new measurement methods for active measurements in reactive networks (e.g., mobile networks).

Secure Smart Grid Communications

Smart Grids are self-organizing intelligent energy-grids that merge electricity, gas, heat and communication-networks. Due to the vital nature of electricity and heat in modern society, security moves into the focus of research when considering the large attack surface of interconnected grids.

Security in smart grids combines proactive measures such as cells, firewalls or security by architecture and reactive measures such as pattern recognition, prediction and anomaly detection. The CN-group places focus on reactive security while working within a proactive environment.



The Big-DAMA project
Big-DAMA – Big Data Analytics for Network Traffic Monitoring and Analysis:


FUSE – Future Self-Organizing Energy Networks:


RASSA – Reference Architecture for a Secure Smart Grid in Austria


synERGY – Security for Cyber-physical Value Networks Exploiting Smart Grid Systems