Quantum Neural Networks under Depolarization Noise: Exploring White-Box Attacks and Defenses
This work addresses vulnerabilities in quantum machine learning models for researchers and practitioners, revealing an incremental insight into noise effects on adversarial attacks.
The paper investigates the impact of depolarization noise on the adversarial robustness of quantum neural networks, finding that contrary to previous results, adding such noise does not enhance robustness in multi-class classification scenarios.
Leveraging the unique properties of quantum mechanics, Quantum Machine Learning (QML) promises computational breakthroughs and enriched perspectives where traditional systems reach their boundaries. However, similarly to classical machine learning, QML is not immune to adversarial attacks. Quantum adversarial machine learning has become instrumental in highlighting the weak points of QML models when faced with adversarial crafted feature vectors. Diving deep into this domain, our exploration shines light on the interplay between depolarization noise and adversarial robustness. While previous results enhanced robustness from adversarial threats through depolarization noise, our findings paint a different picture. Interestingly, adding depolarization noise discontinued the effect of providing further robustness for a multi-class classification scenario. Consolidating our findings, we conducted experiments with a multi-class classifier adversarially trained on gate-based quantum simulators, further elucidating this unexpected behavior.