Model Inversion Robustness: Can Transfer Learning Help?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911871417712640 |
|---|---|
| author | Ho, Sy-Tuyen Hao, Koh Jun Chandrasegaran, Keshigeyan Nguyen, Ngoc-Bao Cheung, Ngai-Man |
| author_facet | Ho, Sy-Tuyen Hao, Koh Jun Chandrasegaran, Keshigeyan Nguyen, Ngoc-Bao Cheung, Ngai-Man |
| contents | Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performance, posing serious threats to privacy. Meanwhile, all existing MI defense methods rely on regularization that is in direct conflict with the training objective, resulting in noticeable degradation in model utility. In this work, we take a different perspective, and propose a novel and simple Transfer Learning-based Defense against Model Inversion (TL-DMI) to render MI-robust models. Particularly, by leveraging TL, we limit the number of layers encoding sensitive information from private training dataset, thereby degrading the performance of MI attack. We conduct an analysis using Fisher Information to justify our method. Our defense is remarkably simple to implement. Without bells and whistles, we show in extensive experiments that TL-DMI achieves state-of-the-art (SOTA) MI robustness. Our code, pre-trained models, demo and inverted data are available at: https://hosytuyen.github.io/projects/TL-DMI |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Model Inversion Robustness: Can Transfer Learning Help? Ho, Sy-Tuyen Hao, Koh Jun Chandrasegaran, Keshigeyan Nguyen, Ngoc-Bao Cheung, Ngai-Man Machine Learning Cryptography and Security Computer Vision and Pattern Recognition Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performance, posing serious threats to privacy. Meanwhile, all existing MI defense methods rely on regularization that is in direct conflict with the training objective, resulting in noticeable degradation in model utility. In this work, we take a different perspective, and propose a novel and simple Transfer Learning-based Defense against Model Inversion (TL-DMI) to render MI-robust models. Particularly, by leveraging TL, we limit the number of layers encoding sensitive information from private training dataset, thereby degrading the performance of MI attack. We conduct an analysis using Fisher Information to justify our method. Our defense is remarkably simple to implement. Without bells and whistles, we show in extensive experiments that TL-DMI achieves state-of-the-art (SOTA) MI robustness. Our code, pre-trained models, demo and inverted data are available at: https://hosytuyen.github.io/projects/TL-DMI |
| title | Model Inversion Robustness: Can Transfer Learning Help? |
| topic | Machine Learning Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.05588 |