# VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation

arXiv: https://arxiv.org/abs/2305.05736 · HTML: https://mlsanity.com/paper/2305.05736/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2023.

## Built on by (most cited first, 14 of 14)

- [SafeEar: Content Privacy-Preserving Audio Deepfake Detection](https://mlsanity.com/paper/2409.09272/) (2024)
- [Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots](https://mlsanity.com/paper/2307.09579/) (2023)
- [Mitigating Unauthorized Speech Synthesis for Voice Protection](https://mlsanity.com/paper/2410.20742/) (2024)
- [Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems](https://mlsanity.com/paper/2311.11796/) (2023)
- [SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis](https://mlsanity.com/paper/2504.09839/) (2025)
- [PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection](https://mlsanity.com/paper/2309.06960/) (2023)
- [SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers](https://mlsanity.com/paper/2401.17133/) (2024)
- [De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks](https://mlsanity.com/paper/2507.02606/) (2025)
- [DynamicFL: Balancing Communication Dynamics and Client Manipulation for Federated Learning](https://mlsanity.com/paper/2308.06267/) (2023)
- [Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes](https://mlsanity.com/paper/2602.22197/) (2026)
- [Protecting Activity Sensing Data Privacy Using Hierarchical Information Dissociation](https://mlsanity.com/paper/2409.03796/) (2024)
- [Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy](https://mlsanity.com/paper/2505.19951/) (2025)
- [Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation](https://mlsanity.com/paper/2512.06304/) (2025)
- [VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion](https://mlsanity.com/paper/2607.11706/) (2026)

## Abstract (arXiv)

Deep learning based voice synthesis technology generates artificial human-like speeches, which has been used in deepfakes or identity theft attacks. Existing defense mechanisms inject subtle adversarial perturbations into the raw speech audios to mislead the voice synthesis models. However, optimizing the adversarial perturbation not only consumes substantial computation time, but it also requires the availability of entire speech. Therefore, they are not suitable for protecting live speech streams, such as voice messages or online meetings. In this paper, we propose VSMask, a real-time protection mechanism against voice synthesis attacks. Different from offline protection schemes, VSMask leverages a predictive neural network to forecast the most effective perturbation for the upcoming streaming speech. VSMask introduces a universal perturbation tailored for arbitrary speech input to shield a real-time speech in its entirety. To minimize the audio distortion within the protected speech, we implement a weight-based perturbation constraint to reduce the perceptibility of the added perturbation. We comprehensively evaluate VSMask protection performance under different scenarios. The experimental results indicate that VSMask can effectively defend against 3 popular voice synthesis models. None of the synthetic voice could deceive the speaker verification models or human ears with VSMask protection. In a physical world experiment, we demonstrate that VSMask successfully safeguards the real-time speech by injecting the perturbation over the air.