SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech

Yuqi Li; Yuanzhong Zheng; Zhongtian Guo; Yaoxuan Wang; Jianjun Yin; Haojun Fei

ICASSP 2025accepted0 citations

SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech

Yuqi Li, Yuanzhong Zheng, Zhongtian Guo, Yaoxuan Wang, Jianjun Yin, Haojun Fei

Abstract

This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction [1] and incorporates spectrogram resizing and incremental training for improved performance. Evaluated on librispeech-dev and librispeech-test, SpecWav-Attack outperforms conventional attacks, revealing vulnerabilities in anonymized speech systems and emphasizing the need for stronger defenses, benchmarked against the ICASSP 2025 Attacker Challenge [2].

BibTeX

@inproceedings{icassp2025_specwavattacklev,
  title = {SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech},
  author = {Yuqi Li and Yuanzhong Zheng and Zhongtian Guo and Yaoxuan Wang and Jianjun Yin and Haojun Fei},
  booktitle = {ICASSP 2025},
  year = {2025}
}