Quantum-inspired analysis of neural network vulnerabilities:the role of conjugate variables in system attacks  

作　　者：Jun-Jie Zhang Deyu Meng 

机构地区：[1]Division of Computational physics and Intelligent modeling,Northwest Institute of Nuclear Technology,Xi’an 710024,China [2]School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security,Xi’an Jiaotong University,Xi’an 710049,China [3]Pazhou Lab,Guangzhou 510335,China

出　　处：《National Science Review》2024年第9期296-303,共8页国家科学评论（英文版）

基　　金：supported by the National Key Research and Development Program of China(2020YFA0713900);the National Natural Science Foundation of China(12105227,12226004 and 62272375)。

摘　　要：Neural networks demonstrate vulnerability to small,non-random perturbations,emerging as adversarial attacks.Such attacks,born from the gradient of the loss function relative to the input,are discerned as input conjugates,revealing a systemic fragility within the network structure.Intriguingly,a mathematical congruence manifests between this mechanism and the quantum physics’uncertainty principle,casting light on a hitherto unanticipated interdisciplinarity.This inherent susceptibility within neural network systems is generally intrinsic,highlighting not only the innate vulnerability of these networks,but also suggesting potential advancements in the interdisciplinary area for understanding these black-box networks.

关 键 词：neural network adversarial attack accuracy-robustness trade-off uncertainty principle quantum physics 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP309[自动化与计算机技术—控制科学与工程]