Zenghui Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zenghui Jiang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Pu Chen
College of Communication Engineering, Army Engineering University of PLA, Nanjing, China
2 shared publications - Shenqian Yin
College of Communication Engineering, Army Engineering University of PLA, Nanjing, China
2 shared publications - Weijun Zeng
Communication Engineering College, Army Engineering University of PLA, Nanjing, Jiangsu, China
2 shared publications - Xingyu Zhou
Army Engineering University of PLA
2 shared publications - Changzhi Han
College of Communication Engineering, Army Engineering University of PLA, Qin Huai District, Nanjing 210007, China
1 shared publication - Lin Li
College of Communication Engineering, Army Engineering University of PLA, Qin Huai District, Nanjing 210007, China
1 shared publication
Latest Publications
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (5) , 999-1003
Transferable Sparse Adversarial Attack on Modulation Recognition With Generative Networks
Although Deep neural networks (DNN) can achieve higher performance in automatic modulation recognition, they are known to vulnerable to adversarial perturbations, which are strategically added to inputs can fool the DNN model. In this letter, we propose a novel sparse attack scheme based on adversarial generative networks, which enables more covert attacks while preserving communication quality. This new scheme incorporates adversarial training into the discriminator, which not only improves attack performance but also enhances the stability of the training process for adversarial generative networks. Experimental results demonstrate that the proposed scheme outperforms other sparse attack approaches in terms of generation time and transferability.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (5) , 999-1003
Transferable Sparse Adversarial Attack on Modulation Recognition With Generative Networks
Although Deep neural networks (DNN) can achieve higher performance in automatic modulation recognition, they are known to vulnerable to adversarial perturbations, which are strategically added to inputs can fool the DNN model. In this letter, we propose a novel sparse attack scheme based on adversarial generative networks, which enables more covert attacks while preserving communication quality. This new scheme incorporates adversarial training into the discriminator, which not only improves attack performance but also enhances the stability of the training process for adversarial generative networks. Experimental results demonstrate that the proposed scheme outperforms other sparse attack approaches in terms of generation time and transferability.
- Open Access
- 5 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3752
Sparse Adversarial Attacks against DL-Based Automatic Modulation Classification
Automatic modulation recognition (AMR) serves as a crucial component in domains such as cognitive radio and electromagnetic countermeasures, acting as a significant prerequisite for the efficient signal processing of receivers. Deep neural networks (DNNs), despite their effectiveness, are known to be vulnerable to adversarial attacks. This vulnerability has inspired the introduction of subtle interference to wireless communication signals—interference so minuscule that it is difficult for the human eye to discern. Such interference can mislead eavesdroppers into erroneous modulation pattern recognition when using DNNs, thereby camouflaging communication signal modulation patterns. Nonetheless, the majority of current camouflage methods used for electromagnetic signal modulation recognition rely on a global perturbation of the signal. They fail to consider the local agility of signal disturbance and the concealment requirements for bait signals that are intercepted by the interceptor. This paper presents a generator framework designed to produce perturbations with sparse properties. Furthermore, we introduce a method to reduce spectral loss, which minimizes the spectral difference between adversarial perturbation and the original signal. This method makes perturbation more challenging to monitor, thereby deceiving enemy electromagnetic signal modulation recognition systems. The experimental results validated that the proposed method significantly outperformed existing methods in terms of generation time. Moreover, it can generate adversarial signals characterized by high deceivability and transferability even under extremely sparse conditions.
- 5 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3752
Open AccessSparse Adversarial Attacks against DL-Based Automatic Modulation Classification
Automatic modulation recognition (AMR) serves as a crucial component in domains such as cognitive radio and electromagnetic countermeasures, acting as a significant prerequisite for the efficient signal processing of receivers. Deep neural networks (DNNs), despite their effectiveness, are known to be vulnerable to adversarial attacks. This vulnerability has inspired the introduction of subtle interference to wireless communication signals—interference so minuscule that it is difficult for the human eye to discern. Such interference can mislead eavesdroppers into erroneous modulation pattern recognition when using DNNs, thereby camouflaging communication signal modulation patterns. Nonetheless, the majority of current camouflage methods used for electromagnetic signal modulation recognition rely on a global perturbation of the signal. They fail to consider the local agility of signal disturbance and the concealment requirements for bait signals that are intercepted by the interceptor. This paper presents a generator framework designed to produce perturbations with sparse properties. Furthermore, we introduce a method to reduce spectral loss, which minimizes the spectral difference between adversarial perturbation and the original signal. This method makes perturbation more challenging to monitor, thereby deceiving enemy electromagnetic signal modulation recognition systems. The experimental results validated that the proposed method significantly outperformed existing methods in terms of generation time. Moreover, it can generate adversarial signals characterized by high deceivability and transferability even under extremely sparse conditions.