mlsanityData to 14 Oct 2026

Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognition

arXiv 2110.09814 ↗First posted 19 Oct 2021cs.SD cs.CL cs.CRcited by 1

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

As an effective method for intellectual property (IP) protection, model watermarking technology has been applied on a wide variety of deep neural networks (DNN), including speech classification models. However, how to design a black-box watermarking scheme for automatic speech recognition (ASR) models is still an unsolved problem, which is a significant demand for protecting remote ASR Application Programming Interface (API) deployed in cloud servers. Due to conditional independence assumption and label-detection-based evasion attack risk of ASR models, the black-box model watermarking scheme for speech classification models cannot apply to ASR models. In this paper, we propose the first black-box model watermarking framework for protecting the IP of ASR models. Specifically, we synthesize trigger audios by spreading the speech clips of model owners over the entire input audios and labeling the trigger audios with the stego texts, which hides the authorship information with linguistic steganography. Experiments on the state-of-the-art open-source ASR system DeepSpeech demonstrate the feasibility of the proposed watermarking scheme, which is robust against five kinds of attacks and has little impact on accuracy.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 12 of its 22 references that are in the map. First posted on arXiv 19 Oct 2021.

Builds on

12 of 22 references.

References · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  3. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  4. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  5. 2017Recent Trends in Deep Learning Based Natural Language Processingcited by 263
  6. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  7. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
  8. 2020Entangled Watermarks as a Defense against Model Extractioncited by 149
  9. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 118
  10. 2019How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNNcited by 66
  11. 2017The Microsoft 2017 Conversational Speech Recognition Systemcited by 52
  12. 2019TS-RNN: Text Steganalysis Based on Recurrent Neural Networkscited by 20

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023Performance-lossless Black-box Model Watermarking
  2. 2025Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge Distillation
  3. 2024Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers
  4. 2025The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures
  5. 2025A Game Between the Defender and the Attacker for Trigger-based Black-box Model Watermarking
  6. 2024ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
  7. 2024NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
  8. 2025ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples