Titulo Estágio
Network traffic classification in docker environments using a federated learning based approach
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
Rua Dom João de Castro nº12, 3030-384 Coimbra, Portugal
Enquadramento
Federated Learning (FL) is a distributed machine learning (ML) approach where multiple devices or agents collaboratively train a ML model. This decentralized architecture has gained attention due to its ability to preserve user data privacy, as data remains local to devices, and only model parameters are shared.
DeepGuardian, designed by OneSource, is a framework that leverages ML models to detect and classify anomalies in network traffic. This framework allows real-time detection and classification of outbound and inbound network traffic from cloud-native applications.
This internship aims to develop and integrate a Federated Learning based approach in Docker environments, maximizing data security and enhancing the privacy of the personal data on the network using Privacy Enhancing Technologies (PETs). Considering the docker’s traditional approach, this implementation – with a strong focus on data security and privacy – will present several challenges, namely, identifying the most suitable tools, technologies, AI algorithms and PETs to be implemented.
Objetivo
The main objectives of this internship are:
● Implement federated learning in docker environments
● Implement PETs to ensure data privacy in docker environments
● Ensure multiple FL clients' support
Plano de Trabalhos - Semestre 1
1. Analysis of the state of the art related to Federated Learning;
2. Analysis of the state of the art related to Docker;
3. Analysis of the state of the art about PETs;
4. Elaboration of PoCs;
5. Writing of the Master thesis (intermedium version);
Plano de Trabalhos - Semestre 2
1. Implement FL approach with multiple clients in a docker environment;
2. Integrate PETs in the FL approach;
3. Testing and validation of the implemented approach;
4. Integration and validation of the developed approach with DeepGuardian;
5. Writing of the Master thesis (final version);
Condições
The trainee will have all the necessary conditions to carry out the planned tasks, being integrated into the research and development teams within European research projects in which OneSource is involved.
Orientador
Luis Miguel Batista Rosa
luis.rosa@onesource.pt 📩