Adversarial Robustness of Partitioned Quantum Classifiers
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917316722163712 |
|---|---|
| author | Kananian, Pouya Jacobsen, Hans-Arno |
| author_facet | Kananian, Pouya Jacobsen, Hans-Arno |
| contents | Adversarial robustness in quantum classifiers is a critical area of study, providing insights into their performance compared to classical models and uncovering potential advantages inherent to quantum machine learning. In the NISQ era of quantum computing, circuit cutting is a notable technique for simulating circuits that exceed the qubit limitations of current devices, enabling the distribution of a quantum circuit's execution across multiple quantum processing units through classical communication. In contrast, when quantum communication is available, teleportation-based methods can be used to support the distribution of the quantum circuit. We study the robustness of partitioned quantum classifiers to adversarial perturbations targeting wire cutting or quantum state teleportation and show a link between such perturbations and implementing adversarial gates within intermediate layers of a quantum classifier. We then proceed to study the latter problem from both a theoretical and experimental perspective. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20403 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adversarial Robustness of Partitioned Quantum Classifiers Kananian, Pouya Jacobsen, Hans-Arno Emerging Technologies Artificial Intelligence Cryptography and Security Machine Learning Quantum Physics Adversarial robustness in quantum classifiers is a critical area of study, providing insights into their performance compared to classical models and uncovering potential advantages inherent to quantum machine learning. In the NISQ era of quantum computing, circuit cutting is a notable technique for simulating circuits that exceed the qubit limitations of current devices, enabling the distribution of a quantum circuit's execution across multiple quantum processing units through classical communication. In contrast, when quantum communication is available, teleportation-based methods can be used to support the distribution of the quantum circuit. We study the robustness of partitioned quantum classifiers to adversarial perturbations targeting wire cutting or quantum state teleportation and show a link between such perturbations and implementing adversarial gates within intermediate layers of a quantum classifier. We then proceed to study the latter problem from both a theoretical and experimental perspective. |
| title | Adversarial Robustness of Partitioned Quantum Classifiers |
| topic | Emerging Technologies Artificial Intelligence Cryptography and Security Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2502.20403 |