SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech
This work addresses security concerns in speech anonymization for privacy-sensitive applications, but it appears incremental as it builds on existing methods like Wav2Vec2.
The paper tackles the problem of detecting speakers in anonymized speech by introducing SpecWav-Attack, which outperforms conventional attacks on librispeech datasets, revealing vulnerabilities in such systems.
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.