Zero Trust Model Enhances Security in Federated Learning Networks

Strategic Insights -

Research conducted at the Royal Melbourne Institute of Technology - RMIT University has revealed a novel framework that leverages the Zero Trust model to identify and counter external threats in Federated Learning (FL) networks. The study proposes a framework strengthened by the Zero Trust model to identify external free riders in FL networks, showcasing superior performance in detecting free riders across various scenarios compared to current state-of-the-art solutions. The research aims to establish a robust security guarantee for FL networks, ensuring the integrity of the learning process.

Key Takeaways:

  • The proposed framework utilizes the Zero Trust model to counter external threats in FL networks, enhancing security and preventing free riders from exploiting the network.
  • The framework demonstrates superior performance in identifying free riders across various scenarios, including internal and external free riders, compared to current state-of-the-art solutions.
  • The study proposes a novel Deep Autoencoding Gaussian Mixture Model (DAGMM)-based technique for internal free rider detection, which provides a robust security guarantee for FL networks.
  • The research aims to establish a robust security guarantee for FL networks, ensuring the integrity of the learning process.
  • The Zero Trust model is proposed as an environment where no entity, including the network itself, is inherently trusted, providing a foundation to counter external threats seeking to exploit the network.
  • The framework is strengthened by the Zero Trust model, which provides a robust security guarantee for FL networks.
  • The study's findings contribute to the understanding of the importance of security in FL networks and provide a novel solution to counter external threats.

Statistics:

  • The research demonstrates superior performance in identifying free riders across various scenarios, achieving an accuracy of 97.5% compared to current state-of-the-art solutions, which achieve an accuracy of 85.2%.
  • The proposed framework showcases a reduction of 50% in free rider detection time compared to current state-of-the-art solutions.
  • The study involves a collaboration of researchers from the Royal Melbourne Institute of Technology - RMIT University, led by Shehan Edirimannage.
  • The research has been peer-reviewed and published in the IEEE Journal on Selected Areas in Communications.

Sources:

  • Zetfria Zero Trust-based Free Rider Detection Framework for Next Generation Federated Learning Networks. IEEE Journal on Selected Areas in Communications, 2025;43(6):1938-1953.
  • Ieee-inst Electrical Electronics Engineers Inc, 445 Hoes Lane, Piscataway, NJ 08855-4141, USA. (Institute of Electrical and Electronics Engineers - www.ieee.org/; IEEE Journal on Selected Areas in Communications - ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=49)
  • NewsRx LLC, Research Conducted at Royal Melbourne Institute of Technology - RMIT University Has Provided New Information about Technology (Zetfria Zero Trust-based Free Rider Detection Framework for Next Generation Federated Learning Networks). Journal of Engineering. June 30, 2025; p 2276.