Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915487016812544 |
|---|---|
| author | DeAlcala, Daniel Morales, Aythami Fierrez, Julian Mancera, Gonzalo Tolosana, Ruben Ortega-Garcia, Javier |
| author_facet | DeAlcala, Daniel Morales, Aythami Fierrez, Julian Mancera, Gonzalo Tolosana, Ruben Ortega-Garcia, Javier |
| contents | Active Membership Inference Test (aMINT) is a method designed to detect whether given data were used during the training of machine learning models. In Active MINT, we propose a novel multitask learning process that involves training simultaneously two models: the original or Audited Model, and a secondary model, referred to as the MINT Model, responsible for identifying the data used for training the Audited Model. This novel multi-task learning approach has been designed to incorporate the auditability of the model as an optimization objective during the training process of neural networks. The proposed approach incorporates intermediate activation maps as inputs to the MINT layers, which are trained to enhance the detection of training data. We present results using a wide range of neural networks, from lighter architectures such as MobileNet to more complex ones such as Vision Transformers, evaluated in 5 public benchmarks. Our proposed Active MINT achieves over 80% accuracy in detecting if given data was used for training, significantly outperforming previous approaches in the literature. Our aMINT and related methodological developments contribute to increasing transparency in AI models, facilitating stronger safeguards in AI deployments to achieve proper security, privacy, and copyright protection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07879 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning DeAlcala, Daniel Morales, Aythami Fierrez, Julian Mancera, Gonzalo Tolosana, Ruben Ortega-Garcia, Javier Computer Vision and Pattern Recognition Artificial Intelligence Active Membership Inference Test (aMINT) is a method designed to detect whether given data were used during the training of machine learning models. In Active MINT, we propose a novel multitask learning process that involves training simultaneously two models: the original or Audited Model, and a secondary model, referred to as the MINT Model, responsible for identifying the data used for training the Audited Model. This novel multi-task learning approach has been designed to incorporate the auditability of the model as an optimization objective during the training process of neural networks. The proposed approach incorporates intermediate activation maps as inputs to the MINT layers, which are trained to enhance the detection of training data. We present results using a wide range of neural networks, from lighter architectures such as MobileNet to more complex ones such as Vision Transformers, evaluated in 5 public benchmarks. Our proposed Active MINT achieves over 80% accuracy in detecting if given data was used for training, significantly outperforming previous approaches in the literature. Our aMINT and related methodological developments contribute to increasing transparency in AI models, facilitating stronger safeguards in AI deployments to achieve proper security, privacy, and copyright protection. |
| title | Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.07879 |