On User Privacy in MNO: Machine Unlearning Techniques for Data Compliance and Security

Artificial Intelligence (AI) integration in network management has significantly improved Quality of Experience (QoE) and achieved high availability, reaching 99.99% uptime with an aim to meet the five 9s standard in Next Generation Networks. Utilizing Closed Loop Automation (CLA) within the management plane, AI-driven systems dynamically allocate network resources based on real-time user data. However, the shift to automated management introduces privacy concerns, as retained user data may violate the GDPR's 'right to be forgotten' requirement. To address this, we propose a machine unlearning framework for precise data removal in Deep Neural Network (DNN) models that is fully integrated into the CLA. This framework ensures compliant data deletion requests while preserving model performance. Our experiments demonstrate the framework's effectiveness by preserving the model's accuracy on validation data by 79.38% compared to the existing benchmark methods of 57.0048%, underscoring its potential in secure, privacy-aware network management. The update is tested on model forecasting Internet usage from a telecommunications dataset and achieves a low complexity while maintaining the model's accuracy over a validation dataset. The method provides a reasonable time to run for the 7 million parameter model. Its ease of integration within the network management plane allows operators to reach compliance with the Data Acts.