Siriwardhana, Yushan

Thumbnail Image
Preferred name
Siriwardhana, Yushan
Official Name
Siriwardhana, Yushan

Research Output

Filters

2
2
Reset filters

Settings

Now showing 1 - 2 of 2
  • Publication
    Federated Learning based Anomaly Detection as an Enabler for Securing Network and Service Management Automation in Beyond 5G Networks
    (IEEE, 2022-06-10)
    Jayasinghe, Suwani 
    ;
    Siriwardhana, Yushan 
    ;
    Porambage, Pawani 
    ;
    Liyanage, Madhusanka 
    ;
    Ylianttila, Mika 
    Network automation is a necessity in order to meet the unprecedented demand in the future networks and zero touch network architecture is proposed to cater such requirements. Closed-loop and artificial intelligence are key enablers in this proposed architecture in critical elements such as security. Apart from the arising privacy concerns, machine learning models can also face resource limitations. Federated learning is a machine learning-based technique that addresses both privacy and com- munication efficiency issues. Therefore, we propose a federated learning-based model incorporating the ZSM architecture for network automation. The paper also contains the simulations and results of the proposed multi-stage federated learning model that uses the UNSW-NB15 dataset.
      306Scopus© Citations 12
  • Publication
    Robust and Resilient Federated Learning for Securing Future Networks
    (IEEE, 2022-06-10)
    Siriwardhana, Yushan 
    ;
    Porambage, Pawani 
    ;
    Liyanage, Madhusanka 
    ;
    Ylianttila, Mika 
    Machine Learning (ML) and Artificial Intelligence (AI) techniques are widely adopted in the telecommunication industry, especially to automate beyond 5G networks. Federated Learning (FL) recently emerged as a distributed ML approach that enables localized model training to keep data decentralized to ensure data privacy. In this paper, we identify the applicabil- ity of FL for securing future networks and its limitations due to the vulnerability to poisoning attacks. First, we investigate the shortcomings of state-of-the-art security algorithms for FL and perform an attack to circumvent FoolsGold algorithm, which is known as one of the most promising defense techniques currently available. The attack is launched with the addition of intelligent noise at the poisonous model updates. Then we propose a more sophisticated defense strategy, a threshold-based clustering mechanism to complement FoolsGold. Moreover, we provide a comprehensive analysis of the impact of the attack scenario and the performance of the defense mechanism.
      191Scopus© Citations 2