Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era
This work addresses the problem of trustworthiness in quantum AI for researchers and practitioners in the NISQ era, offering a foundational roadmap that is incremental in building upon existing QML concepts.
The paper tackles the challenge of ensuring reliable, robust, and secure deployment of quantum machine learning (QML) in safety-critical settings by proposing a roadmap for Trustworthy Quantum Machine Learning (TQML), which integrates uncertainty quantification, adversarial robustness, and privacy preservation, validated on NISQ devices with findings such as correlations between uncertainty and prediction risk and privacy-utility trade-offs driven by noise.
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.