arXiv 1907.030382019-07cs.CRcs.LG

基于量子生成对抗网络的微型飞行器导航数据伪造与鉴别

Faking and Discriminating the Navigation Data of a Micro Aerial Vehicle Using Quantum Generative Adversarial Networks

Carleton University（卡尔顿大学）；Institut Polytechnique de Paris（巴黎理工学院）；Télécom SudParis（南巴黎电信学院）

Michel Barbeau, Joaquin Garcia-Alfaro

备注：: Accepted for publication in IEEE GLOBECOM 2019 Workshop on Quantum Communications and Information Technology 2019 (fifth QCIT workshop of the Emerging Technical Committee on Quantum Communications and Information Technology, QCIT-ETC, cf. http://qcit.committees.comsoc.org/qcit19-workshop/)

摘要：

我们表明，量子生成对抗网络（QGAN）的范例可以被对手用来学习生成欺骗网络物理系统（CPS）监控的数据，并进行隐蔽攻击。作为一个测试案例，考虑到微型飞行器（MAV）的导航数据的想法阐述。提出了一种具体的QGAN设计方案，用于生成伪MAV导航数据。最初，对手完全不知道CPS的动态，从坏人的角度来看方法的强度。提出了一种区分MAV导航数据真伪的设计方案。该设计结合了经典优化、量子比特量子计算和光子量子计算。使用PennyLane软件模拟，他们在一个经典的计算平台进行评估。我们评估了导航数据生成器的学习时间和准确性以及导航数据与空间复杂度的关系，即，解决这个问题所需的量子存储器数量。

英文摘要：

We show that the Quantum Generative Adversarial Network (QGAN) paradigm can be employed by an adversary to learn generating data that deceives the monitoring of a Cyber-Physical System (CPS) and to perpetrate a covert attack. As a test case, the ideas are elaborated considering the navigation data of a Micro Aerial Vehicle (MAV). A concrete QGAN design is proposed to generate fake MAV navigation data. Initially, the adversary is entirely ignorant about the dynamics of the CPS, the strength of the approach from the point of view of the bad guy. A design is also proposed to discriminate between genuine and fake MAV navigation data. The designs combine classical optimization, qubit quantum computing and photonic quantum computing. Using the PennyLane software simulation, they are evaluated over a classical computing platform. We assess the learning time and accuracy of the navigation data generator and discriminator versus space complexity, i.e., the amount of quantum memory needed to solve the problem.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。