Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929758188601344 |
|---|---|
| author | Bouaziz, Wassim El-Mhamdi, El-Mahdi Usunier, Nicolas |
| author_facet | Bouaziz, Wassim El-Mhamdi, El-Mahdi Usunier, Nicolas |
| contents | Protecting the use of audio datasets is a major concern for data owners, particularly with the recent rise of audio deep learning models. While watermarks can be used to protect the data itself, they do not allow to identify a deep learning model trained on a protected dataset. In this paper, we adapt to audio data the recently introduced data taggants approach. Data taggants is a method to verify if a neural network was trained on a protected image dataset with top-$k$ predictions access to the model only. This method relies on a targeted data poisoning scheme by discreetly altering a small fraction (1%) of the dataset as to induce a harmless behavior on out-of-distribution data called keys. We evaluate our method on the Speechcommands and the ESC50 datasets and state of the art transformer models, and show that we can detect the use of the dataset with high confidence without loss of performance. We also show the robustness of our method against common data augmentation techniques, making it a practical method to protect audio datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10269 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification Bouaziz, Wassim El-Mhamdi, El-Mahdi Usunier, Nicolas Cryptography and Security Machine Learning Protecting the use of audio datasets is a major concern for data owners, particularly with the recent rise of audio deep learning models. While watermarks can be used to protect the data itself, they do not allow to identify a deep learning model trained on a protected dataset. In this paper, we adapt to audio data the recently introduced data taggants approach. Data taggants is a method to verify if a neural network was trained on a protected image dataset with top-$k$ predictions access to the model only. This method relies on a targeted data poisoning scheme by discreetly altering a small fraction (1%) of the dataset as to induce a harmless behavior on out-of-distribution data called keys. We evaluate our method on the Speechcommands and the ESC50 datasets and state of the art transformer models, and show that we can detect the use of the dataset with high confidence without loss of performance. We also show the robustness of our method against common data augmentation techniques, making it a practical method to protect audio datasets. |
| title | Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2503.10269 |