About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Edge Computing and IoT: Systems, Management and Security. Third EAI International Conference, ICECI 2022, Virtual Event, December 13-14, 2022, Proceedings

Research Article

Defense Mechanisms Against Audio Adversarial Attacks: Recent Advances and Future Directions

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-28990-3_12,
        author={Routing Li and Meng Xue},
        title={Defense Mechanisms Against Audio Adversarial Attacks: Recent Advances and Future Directions},
        proceedings={Edge Computing and IoT: Systems, Management and Security. Third EAI International Conference, ICECI 2022, Virtual Event, December 13-14, 2022, Proceedings},
        proceedings_a={ICECI},
        year={2023},
        month={3},
        keywords={Adversarial defenses Deep learning Speech recognition Speaker recognition},
        doi={10.1007/978-3-031-28990-3_12}
    }
    
  • Routing Li
    Meng Xue
    Year: 2023
    Defense Mechanisms Against Audio Adversarial Attacks: Recent Advances and Future Directions
    ICECI
    Springer
    DOI: 10.1007/978-3-031-28990-3_12
Routing Li1,*, Meng Xue2
  • 1: School of Software Engineering
  • 2: School of Computer Science
*Contact email: routingli@hust.edu.cn

Abstract

With the popularity of speech and speaker recognition systems in recent years, voice interfaces are increasingly integrated into various Internet of Things (IoT) devices. However, studies have demonstrated that such systems are vulnerable to attacks using manipulated inputs. During the last few years, defense mechanisms have been studied and discussed from various aspects to protect voice systems from such attacks. Notwithstanding, there is lacking survey focus on the defense mechanism of audio adversarial examples. In this paper, we provide a comprehensive survey on state-of-the-art defense methods by illuminating their main concepts, reviewing the recent progress with a novel taxonomy, and discussing the future directions. It promises to bring awareness to the security problems in speech and speaker recognition systems and encourages people to propose more robust defenses against audio adversarial examples.

Keywords
Adversarial defenses Deep learning Speech recognition Speaker recognition
Published
2023-03-31
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-28990-3_12
Copyright © 2022–2025 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