Chaire Cyber CNI

Chaire Cyber CNI – Cybersecurity for Critical Networked Infrastructures

Help us spreading the word: 5th Future-IoT “IoT meets Autonomy”, Berlin 29.8.-2.9.2022

Please help us spreading the news that the registration is open for our 5th Future-IoT.org PhD school on “IoT meets Automation” from Aug 29-Sep2, 2022 in Berlin: https://school.future-iot.org. Below you find the corresponding email. Please share it in your communities via mail, LinkedIN, etc. Looking forward to welcoming many of you and your students in Berlin!

Cyber CNI 2021 fall Research Updates: Update of our Platform

The cyberCNI.fr (https://cyberCNI.fr/) Research Update (Spring/ Fall) happens once per semester. It is the big status event of the chair Cyber CNI. All works around the chair are presenting their progress, current works, and next challenges. In this talk, our research engineer Fabien Autrel presents how we improved our testbed based on Fischertechnik and CyberRange technologies.

Chaire CyberCNI @EDF Paris (21.9.2021) – Hassan CHAITOU, Security risk optimization for learning on heterogeneous quality data

On Sep 21, 2021, we had the pleasure to visit our partner EDF in Paris Palaiseau! Here is another highlight presentation:

Hassan CHAITOU, Security risk optimization for learning on heterogeneous quality data
A classifier is a component used in the automation of “decision-making” or complex data abstraction: intruder detection, speed limitation extraction. For an efficient classifier, the training must be on a large volume of data and be renewed over time by integrating or revoking certain learning data. From a security point of view, this process represents a risk since it offers the attacker various ways of degrading classifier performance (either by forcing classifications mischievous, either by randomly degrading its performance). These two types of attacks require more or less effort from the attacker.

This risk is exacerbated when data comes from sources (network equipment, organizations) corresponding to heterogeneous trust levels. Hassan’s thesis aims at controlling the risk associated with this update via game theory in the case where the confidence in the learning data is not homogeneous.

Chaire CyberCNI @EDF Paris (21.9.2021) – Julius BÜNGER, Keeping software in massive IoT installations up-to-date

On Sep 21, 2021, we had the pleasure to visit our partner EDF in Paris Palaiseau! Here is another highlight presentation:

Julius BÜNGER, Keeping software in massive IoT installations up-to-date
Julius’s thesis will provide solutions to ease the IoT device recycling. An object may become unusable for several reasons, for example a hardware failure, no more energy from the battery or obsolete functions. In that case, it is important to decommission the device, and recycle it. One solution for recycling is to re-use the object in a different application or deployment, if it embeds the necessary functions. It can also be disassembled and its parts can be sent to different recycling industry. In order to make this possible, we need to address the issues of localization, keep-alive,classification and security.

Chaire CyberCNI @EDF Paris (21.9.2021) – Awaleh HOUSSEIN MERANEH, Automated learning and handling of Cyber-Physical Attacks

On Sep 21, 2021, we had the pleasure to visit our partner EDF in Paris Palaiseau! Here is another highlight presentation:

Awaleh HOUSSEIN MERANEH, Automated learning and handling of Cyber-Physical Attacks
Awaleh’s study focuses on industrial control systems, which are one of the applications of cyber-physical systems. The major goal of his thesis is to use side channel leakage parameters to detect abnormalities (system failure, cyber-attacks) in industrial control systems. These leakage parameters include things like sound, power usage, electromagnetic, and so on. Review the existing sound anomaly detection methods for ICS in the literature, and to then propose our own sound anomaly detection approach.

Chaire CyberCNI @EDF Paris (21.9.2021) – Léo LAVAUR, Federated learning for defending Cyber-Attacks

On Sep 21, 2021, we had the pleasure to visit our partner EDF in Paris Palaiseau! Here is another highlight presentation:

Léo LAVAUR, Federated learning for defending Cyber-Attacks
In 2016, Google introduced the concept of Federated Learning (FL), enabling collaborative Machine Learning (ML). FL does not share local data but ML models, offering applications in diverse domains, including cybersecurity. Léo explains how FL has been studied to overcome challenges of collaborative intrusion detection and mitigation systems. His current research focuses on applying these concepts to specific use cases, such as smart factories, autonomous vehicles, or smart healthcare.

View More