Beginning of May 2023, our chairholder Marc-Oliver Pahl visited the School of Cybersecurity and Privacy of Georgia Institute of Technology.
![[FIC2023] Forum International de la Cybersécurité – The chair is once again strongly present from April 5-7 in Lille](https://cybercni.fr/wp-content/uploads/2023/04/download-1024x512.png)
We cordially invite you to meet us at the Forum International de la Cybersécurité in Lille:
5.4.2023 16h30, Area of the Masterclasses and Research Presentations of the CNRS
Marc-Oliver Pahl, “The Metaverse – Risk or Chance: a Cybersecurity Perspective”
6.4.2023 14h00, Pavillon de la Région Bretagne F23, “Protection des infrastructures critiques : un sujet au cœur de l’actualité”
![[RU2/22] Hassan CHAITOU : Optimization of security risk for learning on heterogeneous data](https://cybercni.fr/wp-content/uploads/2022/10/RU222-Hassan-CHAITOU-PhD-Student-Telecom-Paris-1024x576.jpg)
On Oct 17, 2022, our PhD student Hassan CHAITOU presented her latest results regarding “Optimization of security risk for learning on heterogeneous data“: https://youtu.be/BI4r3xikugI
Share and like: On Jan 25, 2021, 5pm CET I Carol Fung (Virginia Commonwealth University, US), will talk about “Security and Privacy Protection for IoT Networks“. Watch the trailer here.
You are cordially invited to join the free live stream on youtube and LinkedIn! To register and subscribe to the series announcements, just enter your mail address in the box on the left at https://talk.cybercni.fr/. Please share the link https://talk.cybercni.fr/2022-01 with your interested friends!
On Sep 21, 2021, we had the pleasure to visit our partner EDF in Paris Palaiseau. Today, Mariana present her work. In her talk, she will explain how to make control of cyber-physical systems resilent, using switched linear control system.
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.
Dear members and friends of the chair CyberCNI.fr, we wish you all the best for the year 2022! May many of your wishes become reality! Click on the video to watch our wishes….
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