Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems
Machine learning is being applied to continuous-variable quantum key distribution (CVQKD) systems as defense countermeasures for attack classification. However, recent studies have demonstrated that most of these detection networks are not immune to adversarial attacks. In this paper, we propose to...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/11/2437 |
| _version_ | 1797597679774072832 |
|---|---|
| author | Xun Tang Pengzhi Yin Zehao Zhou Duan Huang |
| author_facet | Xun Tang Pengzhi Yin Zehao Zhou Duan Huang |
| author_sort | Xun Tang |
| collection | DOAJ |
| description | Machine learning is being applied to continuous-variable quantum key distribution (CVQKD) systems as defense countermeasures for attack classification. However, recent studies have demonstrated that most of these detection networks are not immune to adversarial attacks. In this paper, we propose to implement typical adversarial attack strategies against the CVQKD system and introduce a generalized defense scheme. Adversarial attacks essentially generate data points located near decision boundaries that are linearized based on iterations of the classifier to lead to misclassification. Using the DeepFool attack as an example, we test it on four different CVQKD detection networks and demonstrate that an adversarial attack can fool most CVQKD detection networks. To solve this problem, we propose an improved adversarial perturbation elimination with a generative adversarial network (APE-GAN) scheme to generate samples with similar distribution to the original samples to defend against adversarial attacks. The results show that the proposed scheme can effectively defend against adversarial attacks including DeepFool and other adversarial attacks and significantly improve the security of communication systems. |
| first_indexed | 2024-03-11T03:08:59Z |
| format | Article |
| id | doaj.art-cfbebac9a965465b8e77c19a94d582db |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T03:08:59Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-cfbebac9a965465b8e77c19a94d582db2023-11-18T07:44:56ZengMDPI AGElectronics2079-92922023-05-011211243710.3390/electronics12112437Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution SystemsXun Tang0Pengzhi Yin1Zehao Zhou2Duan Huang3School of Physics and Electronics, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Software, Xinjiang University, Urumqi 830001, ChinaSchool of Computer Science, Central South University, Changsha 410083, ChinaMachine learning is being applied to continuous-variable quantum key distribution (CVQKD) systems as defense countermeasures for attack classification. However, recent studies have demonstrated that most of these detection networks are not immune to adversarial attacks. In this paper, we propose to implement typical adversarial attack strategies against the CVQKD system and introduce a generalized defense scheme. Adversarial attacks essentially generate data points located near decision boundaries that are linearized based on iterations of the classifier to lead to misclassification. Using the DeepFool attack as an example, we test it on four different CVQKD detection networks and demonstrate that an adversarial attack can fool most CVQKD detection networks. To solve this problem, we propose an improved adversarial perturbation elimination with a generative adversarial network (APE-GAN) scheme to generate samples with similar distribution to the original samples to defend against adversarial attacks. The results show that the proposed scheme can effectively defend against adversarial attacks including DeepFool and other adversarial attacks and significantly improve the security of communication systems.https://www.mdpi.com/2079-9292/12/11/2437CVQKDadversarial attackDeepFoolAPE-GAN |
| spellingShingle | Xun Tang Pengzhi Yin Zehao Zhou Duan Huang Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems Electronics CVQKD adversarial attack DeepFool APE-GAN |
| title | Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems |
| title_full | Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems |
| title_fullStr | Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems |
| title_full_unstemmed | Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems |
| title_short | Adversarial Perturbation Elimination with GAN Based Defense in Continuous-Variable Quantum Key Distribution Systems |
| title_sort | adversarial perturbation elimination with gan based defense in continuous variable quantum key distribution systems |
| topic | CVQKD adversarial attack DeepFool APE-GAN |
| url | https://www.mdpi.com/2079-9292/12/11/2437 |
| work_keys_str_mv | AT xuntang adversarialperturbationeliminationwithganbaseddefenseincontinuousvariablequantumkeydistributionsystems AT pengzhiyin adversarialperturbationeliminationwithganbaseddefenseincontinuousvariablequantumkeydistributionsystems AT zehaozhou adversarialperturbationeliminationwithganbaseddefenseincontinuousvariablequantumkeydistributionsystems AT duanhuang adversarialperturbationeliminationwithganbaseddefenseincontinuousvariablequantumkeydistributionsystems |