Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Robust Zero Trust Architecture: Joint Blockchain based Federated learning and Anomaly Detection based Framework

Shiva Raj Pokhrel, Luxing Yang, Sutharshan Rajasegarar, Gang Li

TL;DR

An adaptive algorithm that dynamically adjusts to varying user contexts is introduced, using unsupervised clustering to detect novel anomalies, like zero-day attacks, and to ensure a reliable and scalable trust computation.

Abstract

This paper introduces a robust zero-trust architecture (ZTA) tailored for the decentralized system that empowers efficient remote work and collaboration within IoT networks. Using blockchain-based federated learning principles, our proposed framework includes a robust aggregation mechanism designed to counteract malicious updates from compromised clients, enhancing the security of the global learning process. Moreover, secure and reliable trust computation is essential for remote work and collaboration. The robust ZTA framework integrates anomaly detection and trust computation, ensuring secure and reliable device collaboration in a decentralized fashion. We introduce an adaptive algorithm that dynamically adjusts to varying user contexts, using unsupervised clustering to detect novel anomalies, like zero-day attacks. To ensure a reliable and scalable trust computation, we develop an algorithm that dynamically adapts to varying user contexts by employing incremental anomaly detection and clustering techniques to identify and share local and global anomalies between nodes. Future directions include scalability improvements, Dirichlet process for advanced anomaly detection, privacy-preserving techniques, and the integration of post-quantum cryptographic methods to safeguard against emerging quantum threats.

Robust Zero Trust Architecture: Joint Blockchain based Federated learning and Anomaly Detection based Framework

TL;DR

An adaptive algorithm that dynamically adjusts to varying user contexts is introduced, using unsupervised clustering to detect novel anomalies, like zero-day attacks, and to ensure a reliable and scalable trust computation.

Abstract

This paper introduces a robust zero-trust architecture (ZTA) tailored for the decentralized system that empowers efficient remote work and collaboration within IoT networks. Using blockchain-based federated learning principles, our proposed framework includes a robust aggregation mechanism designed to counteract malicious updates from compromised clients, enhancing the security of the global learning process. Moreover, secure and reliable trust computation is essential for remote work and collaboration. The robust ZTA framework integrates anomaly detection and trust computation, ensuring secure and reliable device collaboration in a decentralized fashion. We introduce an adaptive algorithm that dynamically adjusts to varying user contexts, using unsupervised clustering to detect novel anomalies, like zero-day attacks. To ensure a reliable and scalable trust computation, we develop an algorithm that dynamically adapts to varying user contexts by employing incremental anomaly detection and clustering techniques to identify and share local and global anomalies between nodes. Future directions include scalability improvements, Dirichlet process for advanced anomaly detection, privacy-preserving techniques, and the integration of post-quantum cryptographic methods to safeguard against emerging quantum threats.

Paper Structure

This paper contains 12 sections, 10 equations, 6 figures, 2 algorithms.

Table of Contents

  1. Introduction
  2. Motivation and background
  3. Key ZT Challenges and Releated Work
  4. Proposed Framework: Core Principles and Challenges
  5. Innovations and Benefits
  6. Underlying Analytic Understanding
  7. Addressing Impeding Challenges
  8. Algorithms Design and Evaluation
  9. Anomaly Detection based Trust Computation
  10. Clustering based Anomaly Detection
  11. Evaluation and Future Direction
  12. Concluding Remarks

Figures (6)

  • Figure 1: Comparison of centralized and decentralized approaches for deploying ZTA, our approach considers distributed policy monitoring, trust computation, and continuous authentication to enhance security, scalability, and protection.
  • Figure 2: Abstract View of the proposed Blockchain-enabled Federated Learning (BFL) Framework
  • Figure 3: Comparison of the temporal evolution of accuracy of the global model of the proposed Robust ZTA over communication rounds with that of BFL pokhrel2020federated.
  • Figure 4: Variation of the accuracy of the proposed Robust ZTA over communication rounds with that of BFL pokhrel2020federated.
  • Figure 5: System level delay comparison of the proposed Robust ZTA over communication rounds with that of BFL pokhrel2020federated.
  • ...and 1 more figures