Tensor Networks for Explainable Machine Learning in Cybersecurity

TL;DR

This paper demonstrates how tensor networks, specifically Matrix Product States, can be used to develop explainable machine learning models that rival deep learning in performance while offering enhanced interpretability, especially in cybersecurity threat detection.

Contribution

The paper introduces an unsupervised clustering algorithm based on tensor networks that improves interpretability without sacrificing accuracy in cybersecurity applications.

Findings

MPS-based clustering rivals deep learning models in performance.

Tensor networks enable extraction of feature probabilities and information measures.

Enhanced transparency aids understanding AI decision rationale.

Abstract

In this paper we show how tensor networks help in developing explainability of machine learning algorithms. Specifically, we develop an unsupervised clustering algorithm based on Matrix Product States (MPS) and apply it in the context of a real use-case of adversary-generated threat intelligence. Our investigation proves that MPS rival traditional deep learning models such as autoencoders and GANs in terms of performance, while providing much richer model interpretability. Our approach naturally facilitates the extraction of feature-wise probabilities, Von Neumann Entropy, and mutual information, offering a compelling narrative for classification of anomalies and fostering an unprecedented level of transparency and interpretability, something fundamental to understand the rationale behind artificial intelligence decisions.