Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines†This work is dedicated to the memory of Peter Wittek. Issue 4 (15th July 2021)

• Record Type: Journal Article
• Authors: Kehoe, Aidan; Wittek, Peter; Xue, Yanbo; Pozas-Kerstjens, Alejandro
• Is Part Of: Machine learning: science and technology. Volume 2:Issue 4(2021)
• Publication Date: 2021-07-15
• Subjects: generative models -- Boltzmann machines -- quantum machine learning -- adversarial attacks -- machine learning security; 006.31
• DOI: 10.1088/2632-2153/abf834
• Languages: English
• ISSNs: 2632-2153

Abstract

Abstract: We provide a robust defence to adversarial attacks on discriminative algorithms. Neural networks are naturally vulnerable to small, tailored perturbations in the input data that lead to wrong predictions. On the contrary, generative models attempt to learn the distribution underlying a dataset, making them inherently more robust to small perturbations. We use Boltzmann machines for discrimination purposes as attack-resistant classifiers, and compare them against standard state-of-the-art adversarial defences. We find improvements ranging from 5% to 72% against attacks with Boltzmann machines on the MNIST dataset. We furthermore complement the training with quantum-enhanced sampling from the D-Wave 2000Q annealer, finding results comparable with classical techniques and with marginal improvements in some cases. These results underline the relevance of probabilistic methods in constructing neural networks and highlight a novel scenario of practical relevance where quantum computers, even with limited hardware capabilities, could provide advantages over classical computers.