About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Wireless and Satellite Systems. 12th EAI International Conference, WiSATS 2021, Virtual Event, China, July 31 – August 2, 2021, Proceedings

Research Article

Momentum-Based Adversarial Attacks Against End-to-End Communication Systems

Download(Requires a free EAI acccount)
4 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-030-93398-2_48,
        author={Qiuna Zhang and Yongkui Ma and Honglin Zhao and Chengzhao Shan and Jiayan Zhang},
        title={Momentum-Based Adversarial Attacks Against End-to-End Communication Systems},
        proceedings={Wireless and Satellite Systems. 12th EAI International Conference, WiSATS 2021, Virtual Event, China, July 31 -- August 2, 2021, Proceedings},
        proceedings_a={WISATS},
        year={2022},
        month={1},
        keywords={Momentum Adversarial attacks End-to-end communication systems Deep learning Wireless security Model robustness},
        doi={10.1007/978-3-030-93398-2_48}
    }
    
  • Qiuna Zhang
    Yongkui Ma
    Honglin Zhao
    Chengzhao Shan
    Jiayan Zhang
    Year: 2022
    Momentum-Based Adversarial Attacks Against End-to-End Communication Systems
    WISATS
    Springer
    DOI: 10.1007/978-3-030-93398-2_48
Qiuna Zhang1, Yongkui Ma1, Honglin Zhao1,*, Chengzhao Shan1, Jiayan Zhang1
  • 1: Communication Research Center
*Contact email: hlzhao@hit.edu.cn

Abstract

Deep learning (DL) based communication system is a promising novel architecture to implement end-to-end optimization compared with conventional block-separated optimization schemes. However, the vulnerability to adversarial examples of deep neural networks poses significant security concern on the end-to-end communication systems. Adversarial attacks serve as a fundamental surrogate to evaluate the robustness of the DL-based communication systems before they are deployed. Specifically, we propose a new adversarial attack method with momentum iterative gradient against the end-to-end communication systems. For targeted attacks, embedding the momentum term in the iterative process can help loss function stabilize the update direction and avoid getting stuck in saddle points and poor local minima. Therefore, the momentum-based method can enhance the effectiveness without losing the transferability of adversarial attacks. Numerous simulation results illustrate that the proposed method can achieve superior block error rate compared with traditional jamming attacks and no momentum accumulated adversarial attacks.

Keywords
Momentum Adversarial attacks End-to-end communication systems Deep learning Wireless security Model robustness
Published
2022-01-21
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-030-93398-2_48
Copyright © 2021–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL