[RU1/21] Leo LAVAUR, Federated detection and defense against cyber-attacks

September 1, 2021July 23, 2021 By Marc-Oliver Pahl Member presentation / personnelcollaborative security,cybersecurity,decentralized machine learning model,deep learning,distributed deep learning,evaluating machine learning models,machine learning,machine learning (software genre),machine learning companies,machine learning developer,machine learning model,machine learning on decentralized data,machine learning platform development,training machine learning models

Leo LAVAUR is at the chaire since October 2020 Airbus, BNP Parisbas, EDF, Nokia and SNCF.

The Internet of Things has begun to spread over avariety of domains, including industry and finance. It represents an increasing threat for both IT and OT. The lack of collaboration results in the same attacks targeting different organizations one after the other. Often employed as an answer to this problem, cyber threat-intelligence sharing induces its own set of challenges :trust, privacy, and traceability. This thesis takes advantages of a distributed sharing-oriented architecture to enhance the security of industrial infrastructures. We study Federated Learning algorithms to build a distributed, autonomic system for detecting and characterizing attacks, as well as providing counter-measures. Experiments on real-world testbeds at the chair Cyber CNI allow us to validate the theoretical assumptions against realistic infrastructures and scenarios, fitting industrial use-cases.

Author
Recent Posts

Léo Lavaur

PhD Student at IMT Atlantique

Léo Lavaur has joined the doctoral program of IMT Atlantique in October 2020 to start his PhD in the chair Cyber CNI. Prior to his admission, Léo earned an engineering degree in information security from ENSIBS, Vannes, France, where he acquired skills and knowledge on the whole spectrum of cybersecurity—from reverse engineering to geostrategy and ethics. Three years as apprentice engineer at Orange Cyberdefense allowed him to acquire operational skills.

Léo’s research focuses on federated architectures, intrusion detection, and machine learning. He studies the collaboration in security systems, and how to share data without compromising security. With the chair and its test bed, he works on building a distributed observatory for attack detection, characterization, and mitigation.