MINT-Demo: Membership Inference Test Demonstrator
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929753203671040 |
|---|---|
| author | DeAlcala, Daniel Morales, Aythami Fierrez, Julian Mancera, Gonzalo Tolosana, Ruben Vera-Rodriguez, Ruben |
| author_facet | DeAlcala, Daniel Morales, Aythami Fierrez, Julian Mancera, Gonzalo Tolosana, Ruben Vera-Rodriguez, Ruben |
| contents | We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determining whether certain data has been used during the training of machine learning models. We conduct experiments with popular face recognition models and 5 public databases containing over 22M images. Promising results, up to 89% accuracy are achieved, suggesting that it is possible to recognize if an AI model has been trained with specific data. Finally, we present a MINT platform as demonstrator of this technology aimed to promote transparency in AI training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08332 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MINT-Demo: Membership Inference Test Demonstrator DeAlcala, Daniel Morales, Aythami Fierrez, Julian Mancera, Gonzalo Tolosana, Ruben Vera-Rodriguez, Ruben Computer Vision and Pattern Recognition Artificial Intelligence We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determining whether certain data has been used during the training of machine learning models. We conduct experiments with popular face recognition models and 5 public databases containing over 22M images. Promising results, up to 89% accuracy are achieved, suggesting that it is possible to recognize if an AI model has been trained with specific data. Finally, we present a MINT platform as demonstrator of this technology aimed to promote transparency in AI training. |
| title | MINT-Demo: Membership Inference Test Demonstrator |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.08332 |