| Autor: |
Drasko Draskovic, Dusan Borovcanin, Srdjan Penjivrag, Francois Carrez, S. Abdelkareem, Roumpis, Spiros, Stavroulaki, Vera, Demestichas, Panagiotis |
| Rok vydání: |
2021 |
| DOI: |
10.5281/zenodo.6780077 |
| Popis: |
This deliverable reports the activity conducted on Mechanisms for Security, Privacy, and trust. It will include initial specification of the DEDICAT 6G security and data protection framework and DEDICAT 6G trust management platform, architectures, tools, Key Performance Indicators (KPI) and set of standards and best practices to follow towards realization of the security and privacy protection tasks. D5.1 will specify a federated learning mechanism for distributed training of machine learning models for threat detection and classification. System logs and key event information will be used for training local ML models within ecosystem of communication and computation networks formed with the project’s framework. In this way highest level of privacy protection is ensured since data for model training are not transferred to a centralized entity. Also, focus will be specification and implementation of trust management platform for DEDICAT 6G dynamic networking and computational distributed systems. This platform would be responsible to ensure the integrity of highly dynamic and distributed communication and computation systems by building certification mechanisms and compliance tests for all nodes, applications and services which comprise such systems. Validation mechanism will be detailed in the future deliverables. The Key Performance Indicators measured in the WP 5 include: Adopted best practices and IoT domain standards for security and data protection to build ML models. Federated learning global models for security and data protection threat detection and classification Federated learning mechanisms implemented Implemented federated learning mechanisms for multiple system layers: federated learning local enabler for mobile platforms, microprocessor environments and lo-cal servers. Implemented blockchain data architecture/network for the project trust management platform (various configurations to be tested with ChainRider blockchain as a service solution) Configured and validated smart contract templates for trusted data exchange within project use cases and automated auditing of the edge computing system status |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
