Computable Model-Independent Bounds for Adversarial Quantum Machine Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Bacui, Alpcan, Tansu, Thapa, Chandra, Parampalli, Udaya
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912113549639680
author Li, Bacui
Alpcan, Tansu
Thapa, Chandra
Parampalli, Udaya
author_facet Li, Bacui
Alpcan, Tansu
Thapa, Chandra
Parampalli, Udaya
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06863
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Computable Model-Independent Bounds for Adversarial Quantum Machine Learning
Li, Bacui
Alpcan, Tansu
Thapa, Chandra
Parampalli, Udaya
Machine Learning
Artificial Intelligence
Emerging Technologies
Quantum Physics
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.
title Computable Model-Independent Bounds for Adversarial Quantum Machine Learning
topic Machine Learning
Artificial Intelligence
Emerging Technologies
Quantum Physics
url https://arxiv.org/abs/2411.06863