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

Yuqi Li, Yuanzhong Zheng, Zhongtian Guo, Yaoxuan Wang, Jianjun Yin +1 more
1/10/2025
cs.SDcs.AIeess.AS

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction 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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

DAST: A Dual-Stream Voice Anonymization Attacker with Staged Training

86% match1 repo2026

Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems

85% match1 repo112025

Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models

84% match1 repo12024

USTC-KXDIGIT System Description for ASVspoof5 Challenge

83% match2024

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems

83% match2025

SpoofCeleb: Speech Deepfake Detection and SASV In The Wild

82% match2024

Cite this paper

@article{li2025specwavattack,
  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},
  year   = {2025},
  eprint = {2505.09616},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.09616v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.09616.svg)](https://codeofpaper.com/paper/2505.09616)

Discussion