HFAD: Homomorphic Filtering Adversarial Defense Against Adversarial Attacks in Automatic Modulation Classification
- 31 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 10 (3) , 880-892
Abstract
Deep neural networks provide intelligent solutions for Automatic Modulation Classification (AMC) tasks in the field of communication. However, their susceptibility to adversarial examples due to the interpretability problem presents a challenge as it leads to anomalous decisions. Emerging studies suggest that the high-frequency constituents within signals constitute a fundamental source of adversarial vulnerability. To address this issue, this paper introduces a Homomorphic Filtering Adversarial Defense (HFAD) algorithm that aims to effectively defend against adversarial examples by applying frequency domain filtering on the signal. This approach enhances the security and reliability of the AMC model by attenuating high-frequency components of the signal through homomorphic filtering, thereby reducing errors caused by adversarial perturbations on model outputs. The robustness of the AMC model is further enhanced through the integration of HFAD with data augmentation strategies. Experimental results demonstrate that the proposed defense algorithm not only maintains high signal recognition accuracy but also preserves communication signal transmission quality. Moreover, HFAD effectively withstands a wide range of white-box adversarial attacks and demonstrates resilience against black-box adversarial attacks, thereby enhancing the robustness of the AMC model against adversarial examples and exhibiting strong transfer performance.Keywords
Funding Information
- National Natural Science Foundation of China (62201172)
- National Key Research and Development Program of China (2022YFE0136800)
- Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin Engineering University, Harbin, China
- National Natural Science Foundation of China (U21B2001)
- Key R&D Program of Zhejiang (2022C01018)
This publication has 33 references indexed in Scilit:
- Adversarial attacks and defenses for digital communication signals identificationDigital Communications and Networks, 2024
- Low-Light Homomorphic Filtering Network for integrating image enhancement and classificationSignal Processing: Image Communication, 2022
- High frequency patterns play a key role in the generation of adversarial examplesNeurocomputing, 2021
- Dissecting the High-Frequency Bias in Convolutional Neural Networks2021
- Attack Selectivity of Adversarial Examples in Remote Sensing Image Scene ClassificationIEEE Access, 2020
- High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks2020
- Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples2019
- On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions2019
- Boosting Adversarial Attacks with Momentum2018
- Regularized Laplacian Zero Crossings as Optimal Edge IntegratorsInternational Journal of Computer Vision, 2003