A quantum active learning algorithm for sampling against adversarial attacks

Downloads

Downloads per month over past year

63519

Impacto

Downloads

Downloads per month over past year

Moreno Casares, Pablo Antonio and Martín-Delgado Alcántara, Miguel Ángel (2020) A quantum active learning algorithm for sampling against adversarial attacks. New journal of physics, 22 (7). ISSN 1367-2630

[thumbnail of Martín Delgado Alcántara MÁ 128 LIBRE+CC.pdf]
Preview
PDF
Creative Commons Attribution.

2MB

Official URL: http://dx.doi.org/10.1088/1367-2630/ab976f




Abstract

Adversarial attacks represent a serious menace for learning algorithms and may compromise the security of future autonomous systems. A theorem by Khoury and Hadfield-Menell (KH), provides sufficient conditions to guarantee the robustness of active learning algorithms, but comes with a caveat: it is crucial to know the smallest distance among the classes of the corresponding classification problem. We propose a theoretical framework that allows us to think of active learning as sampling the most promising new points to be classified, so that the minimum distance between classes can be found and the theorem KH used. Additionally, we introduce a quantum active learning algorithm that makes use of such framework and whose complexity is polylogarithmic in the dimension of the space, m, and the size of the initial training data n, provided the use of qRAMs; and polynomial in the precision, achieving an exponential speedup over the equivalent classical algorithm in n and m.


Item Type:Article
Additional Information:

© 2020 The Author(s).
We would like to thank Santiago Varona for useful comments on the manuscript, as well to Jaime Sevilla, Nikolas Bernaola and Javier Prieto for pointing us to useful statistic results for appendix C. We acknowledge financial support from the Spanish MINECO grants MINECO/FEDER Projects FIS 2017-91460-EXP, PGC2018-099169-B-I00 FIS-2018 and from CAM/FEDER Project No. S2018/TCS-4342 (QUITEMAD-CM). The research of MAM-D has been partially supported by the US Army Research Office through Grant No.W911NF-14-1-0103. PAMC thanks the support of an FPU MECD Grant.

Uncontrolled Keywords:quantum algorithm; active learning; quantum machine Learning; Adversarial example; Support vector machine; qRAM; Quantum advantage
Subjects:Sciences > Physics
ID Code:63519
Deposited On:20 Jan 2021 19:34
Last Modified:21 Jan 2021 07:55

Origin of downloads

Repository Staff Only: item control page