Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sadhukhan, Deepsayan, Shankar, Nitin Priyadarshini, Kalyani, Sheetal
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Machine Learning Signal Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866914951645364224
author	Sadhukhan, Deepsayan Shankar, Nitin Priyadarshini Kalyani, Sheetal
author_facet	Sadhukhan, Deepsayan Shankar, Nitin Priyadarshini Kalyani, Sheetal
contents	We propose a minimal power white box adversarial attack for Deep Learning based Automatic Modulation Classification (AMC). The proposed attack uses the Golden Ratio Search (GRS) method to find powerful attacks with minimal power. We evaluate the efficacy of the proposed method by comparing it with existing adversarial attack approaches. Additionally, we test the robustness of the proposed attack against various state-of-the-art architectures, including defense mechanisms such as adversarial training, binarization, and ensemble methods. Experimental results demonstrate that the proposed attack is powerful, requires minimal power, and can be generated in less time, significantly challenging the resilience of current AMC methods.
format	Preprint
id	arxiv_https___arxiv_org_abs_2409_11454
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification Sadhukhan, Deepsayan Shankar, Nitin Priyadarshini Kalyani, Sheetal Cryptography and Security Machine Learning Signal Processing We propose a minimal power white box adversarial attack for Deep Learning based Automatic Modulation Classification (AMC). The proposed attack uses the Golden Ratio Search (GRS) method to find powerful attacks with minimal power. We evaluate the efficacy of the proposed method by comparing it with existing adversarial attack approaches. Additionally, we test the robustness of the proposed attack against various state-of-the-art architectures, including defense mechanisms such as adversarial training, binarization, and ensemble methods. Experimental results demonstrate that the proposed attack is powerful, requires minimal power, and can be generated in less time, significantly challenging the resilience of current AMC methods.
title	Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification
topic	Cryptography and Security Machine Learning Signal Processing
url	https://arxiv.org/abs/2409.11454