Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915596880314368 |
|---|---|
| author | Catak, Ferhat Ozgur Seo, Jungwon Cali, Umit |
| author_facet | Catak, Ferhat Ozgur Seo, Jungwon Cali, Umit |
| contents | Quantum machine learning (QML) is a promising paradigm for tackling computational problems that challenge classical AI. Yet, the inherent probabilistic behavior of quantum mechanics, device noise in NISQ hardware, and hybrid quantum-classical execution pipelines introduce new risks that prevent reliable deployment of QML in real-world, safety-critical settings. This research offers a broad roadmap for Trustworthy Quantum Machine Learning (TQML), integrating three foundational pillars of reliability: (i) uncertainty quantification for calibrated and risk-aware decision making, (ii) adversarial robustness against classical and quantum-native threat models, and (iii) privacy preservation in distributed and delegated quantum learning scenarios. We formalize quantum-specific trust metrics grounded in quantum information theory, including a variance-based decomposition of predictive uncertainty, trace-distance-bounded robustness, and differential privacy for hybrid learning channels. To demonstrate feasibility on current NISQ devices, we validate a unified trust assessment pipeline on parameterized quantum classifiers, uncovering correlations between uncertainty and prediction risk, an asymmetry in attack vulnerability between classical and quantum state perturbations, and privacy-utility trade-offs driven by shot noise and quantum channel noise. This roadmap seeks to define trustworthiness as a first-class design objective for quantum AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era Catak, Ferhat Ozgur Seo, Jungwon Cali, Umit Quantum Physics Artificial Intelligence Quantum machine learning (QML) is a promising paradigm for tackling computational problems that challenge classical AI. Yet, the inherent probabilistic behavior of quantum mechanics, device noise in NISQ hardware, and hybrid quantum-classical execution pipelines introduce new risks that prevent reliable deployment of QML in real-world, safety-critical settings. This research offers a broad roadmap for Trustworthy Quantum Machine Learning (TQML), integrating three foundational pillars of reliability: (i) uncertainty quantification for calibrated and risk-aware decision making, (ii) adversarial robustness against classical and quantum-native threat models, and (iii) privacy preservation in distributed and delegated quantum learning scenarios. We formalize quantum-specific trust metrics grounded in quantum information theory, including a variance-based decomposition of predictive uncertainty, trace-distance-bounded robustness, and differential privacy for hybrid learning channels. To demonstrate feasibility on current NISQ devices, we validate a unified trust assessment pipeline on parameterized quantum classifiers, uncovering correlations between uncertainty and prediction risk, an asymmetry in attack vulnerability between classical and quantum state perturbations, and privacy-utility trade-offs driven by shot noise and quantum channel noise. This roadmap seeks to define trustworthiness as a first-class design objective for quantum AI. |
| title | Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era |
| topic | Quantum Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2511.02602 |