In this work, we give an overview on some recent results related to quantum machine learning (QML) regarding the training of quantum generative adversarial neural networks by means of classical shadows, and a parametric model implemented on a quantum annealer. Then, we argue that QML models can be robust against targeted data corruption and gradient-based attacks, motivating the exploration of the relationship between QML and cybersecurity.
Pastorello, D. (2024). Quantum Machine Learning: Perspectives in Cybersecurity [10.1007/978-3-031-68738-9_20].
Quantum Machine Learning: Perspectives in Cybersecurity
Pastorello, Davide
2024
Abstract
In this work, we give an overview on some recent results related to quantum machine learning (QML) regarding the training of quantum generative adversarial neural networks by means of classical shadows, and a parametric model implemented on a quantum annealer. Then, we argue that QML models can be robust against targeted data corruption and gradient-based attacks, motivating the exploration of the relationship between QML and cybersecurity.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Quantum_cybersecurity.pdf
embargo fino al 08/09/2025
Tipo:
Postprint
Licenza:
Licenza per accesso libero gratuito
Dimensione
415.57 kB
Formato
Adobe PDF
|
415.57 kB | Adobe PDF | Visualizza/Apri Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
