Quantum Adversarial Learning for Kernel Methods
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916198287933440 |
|---|---|
| author | Montalbano, Giuseppe Banchi, Leonardo |
| author_facet | Montalbano, Giuseppe Banchi, Leonardo |
| contents | We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defence strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05824 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantum Adversarial Learning for Kernel Methods Montalbano, Giuseppe Banchi, Leonardo Quantum Physics Cryptography and Security Machine Learning We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defence strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment. |
| title | Quantum Adversarial Learning for Kernel Methods |
| topic | Quantum Physics Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2404.05824 |