首次计算出量子机器学习抗攻击的理论下界，验证其内在鲁棒性。
Computable Model-Independent Bounds for Adversarial Quantum Machine Learning
- 基于量子力学原理推导模型无关的对抗性能下界
- 实验误差仅比理论下界高10%，表明量子模型具强鲁棒性
- 为未来鲁棒量子算法设计提供精确参考基准
量子机器学习（QML）利用量子力学原理，为机器学习带来新方法并具备潜在加速优势。然而，机器学习模型普遍易受恶意扰动，该脆弱性同样存在于QML中。随着量子计算能力扩展，深入理解QML对对抗攻击的韧性至关重要。本文首次计算了针对复杂量子对抗攻击的模型无关近似下界，评估模型韧性。实验结果与计算下界对比显示，最佳情况下实验误差仅比估计下界高出10%，表明量子模型具有内在鲁棒性。该研究不仅深化了对量子模型韧性的理论认识，也为未来鲁棒QML算法的发展提供了精确参考边界。
原文摘要 · Abstract (English)
By leveraging the principles of quantum mechanics, QML opens doors to novel approaches in machine learning and offers potential speedup. However, machine learning models are well-documented to be vulnerable to malicious manipulations, and this susceptibility extends to the models of QML. This situation necessitates a thorough understanding of QML's resilience against adversarial attacks, particularly in an era where quantum computing capabilities are expanding. In this regard, this paper examines model-independent bounds on adversarial performance for QML. To the best of our knowledge, we introduce the first computation of an approximate lower bound for adversarial error when evaluating model resilience against sophisticated quantum-based adversarial attacks. Experimental results are compared to the computed bound, demonstrating the potential of QML models to achieve high robustness. In the best case, the experimental error is only 10% above the estimated bound, offering evidence of the inherent robustness of quantum models. This work not only advances our theoretical understanding of quantum model resilience but also provides a precise reference bound for the future development of robust QML algorithms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。