# Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning

arXiv: https://arxiv.org/abs/2006.03214 · HTML: https://mlsanity.com/paper/2006.03214/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [Adversarial defense for automatic speaker verification by cascaded self-supervised learning models](https://mlsanity.com/paper/2102.07047/) (2021)
- [Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning](https://mlsanity.com/paper/2106.00273/) (2021)
- [Partially Fake Audio Detection by Self-attention-based Fake Span Discovery](https://mlsanity.com/paper/2202.06684/) (2022)
- [Voting for the right answer: Adversarial defense for speaker verification](https://mlsanity.com/paper/2106.07868/) (2021)
- [Adversarial Sample Detection for Speaker Verification by Neural Vocoders](https://mlsanity.com/paper/2107.00309/) (2021)
- [Practical Attacks on Voice Spoofing Countermeasures](https://mlsanity.com/paper/2107.14642/) (2021)
- [Characterizing the adversarial vulnerability of speech self-supervised learning](https://mlsanity.com/paper/2111.04330/) (2021)
- [Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models](https://mlsanity.com/paper/2205.14851/) (2022)
- [Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection](https://mlsanity.com/paper/2210.00753/) (2022)
- [Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification](https://mlsanity.com/paper/2203.17031/) (2022)
- [Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion](https://mlsanity.com/paper/2206.09131/) (2022)
- [DTA: Distribution Transform-based Attack for Query-Limited Scenario](https://mlsanity.com/paper/2312.07245/) (2023)

## Abstract (arXiv)

High-performance anti-spoofing models for automatic speaker verification (ASV), have been widely used to protect ASV by identifying and filtering spoofing audio that is deliberately generated by text-to-speech, voice conversion, audio replay, etc. However, it has been shown that high-performance anti-spoofing models are vulnerable to adversarial attacks. Adversarial attacks, that are indistinguishable from original data but result in the incorrect predictions, are dangerous for anti-spoofing models and not in dispute we should detect them at any cost. To explore this issue, we proposed to employ Mockingjay, a self-supervised learning based model, to protect anti-spoofing models against adversarial attacks in the black-box scenario. Self-supervised learning models are effective in improving downstream task performance like phone classification or ASR. However, their effect in defense for adversarial attacks has not been explored yet. In this work, we explore the robustness of self-supervised learned high-level representations by using them in the defense against adversarial attacks. A layerwise noise to signal ratio (LNSR) is proposed to quantize and measure the effectiveness of deep models in countering adversarial noise. Experimental results on the ASVspoof 2019 dataset demonstrate that high-level representations extracted by Mockingjay can prevent the transferability of adversarial examples, and successfully counter black-box attacks.