.png){kind=icon}
.png){kind=icon}
Return
Quantum adversarial learning for kernel methods
.png){kind=icon}
OA
AI
DOI：10.1007/s42484-025-00238-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defense strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment.
Keywords:
Kernel methods
QSVM
Adversarial learning
Journal
Q
IF:
4.4
Papers:
431
Citations:
796