Description
The emergence of Federated Learning (FL) has rekindled the interest in collaborative intrusion detection systems, which were previously limited by the risks of information disclosure associated with data sharing. But is it a good collaboration tool? Originally designed to train prediction models on distributed consumer data without compromising data confidentiality, its use as a collaborative platform has been less studied. In this talk, I will present our work on federated learning as a mean of collaboration between organizations and the associated scientific challenges, in particular regarding guaranteeing trust in a heterogeneous context. Then, I will discuss our ongoing work on using telemetry to solve the challenge of partial observability in distributed systems and the opportunities for security monitoring. Finally, we will discuss the research directions enabled by these works, and particularly the challenges for building an interpretable and adaptable collaborative platform that maintains strong privacy guarantees.