Saved in:
Bibliographic Details
Main Authors: Zhang, Jun-Jie, Meng, Deyu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.10983
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913236150910976
author Zhang, Jun-Jie
Meng, Deyu
author_facet Zhang, Jun-Jie
Meng, Deyu
contents Neural networks demonstrate inherent 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_10983
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks
Zhang, Jun-Jie
Meng, Deyu
Machine Learning
Cryptography and Security
Quantum Physics
Neural networks demonstrate inherent 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.
title Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks
topic Machine Learning
Cryptography and Security
Quantum Physics
url https://arxiv.org/abs/2402.10983