A quantum active learning algorithm for sampling against adversarial attacks

Author:

Casares P A MORCID,Martin-Delgado M AORCID

Abstract

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.

Funder

Ministerio de Economía y Competitividad

Comunidad de Madrid

Ministerio de Ciencia e Innovación

Army Research Office

Publisher

IOP Publishing

Subject

General Physics and Astronomy

Reference50 articles.

1. Quantum algorithms for supervised and unsupervised machine learning;Lloyd,2013

2. An introduction to quantum machine learning;Schuld;Contemp. Phys.,2015

3. Quantum machine learning;Biamonte;Nature,2017

4. Quantum speedup for active learning agents;Paparo;Phys. Rev. X,2014

5. Active learning machine learns to create new quantum experiments;Melnikov;Proc. Natl Acad. Sci.,2018

Cited by 10 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Active Learning in Physics: From 101, to Progress, and Perspective;Advanced Quantum Technologies;2023-10-24

2. Study of Adversarial Machine Learning for Enhancing Human Action Classification;2022 IEEE 23rd International Conference on Information Reuse and Integration for Data Science (IRI);2022-08

3. Quantum linear system algorithm applied to communication systems;Quantum Information Processing;2022-07-28

4. Active learning for the optimal design of multinomial classification in physics;Physical Review Research;2022-03-21

5. The Dilemma of Quantum Neural Networks;IEEE Transactions on Neural Networks and Learning Systems;2022

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3