Tensor Networks for Explainable Machine Learning in Cybersecurity
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912345382453248 |
|---|---|
| author | Aizpurua, Borja Palmer, Samuel Orus, Roman |
| author_facet | Aizpurua, Borja Palmer, Samuel Orus, Roman |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00867 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Tensor Networks for Explainable Machine Learning in Cybersecurity Aizpurua, Borja Palmer, Samuel Orus, Roman Machine Learning Artificial Intelligence Quantum Physics 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. |
| title | Tensor Networks for Explainable Machine Learning in Cybersecurity |
| topic | Machine Learning Artificial Intelligence Quantum Physics |
| url | https://arxiv.org/abs/2401.00867 |