Abstract
Valuable datasets that contain sensitive information are not shared due to privacy and copyright concerns. This hinders progress in many areas and prevents the use of machine learning solutions to solve relevant tasks. One possible solution is sharing models that are trained on such datasets. However, this is also associated with potential privacy risks due to data extraction attacks. In this work, we propose a solution based on sharing parts of the model’s parameters, and using a proxy dataset for complimentary knowledge transfer. Our experiments show encouraging results, and reduced risk to potential training data identification attacks. We present a viable solution to sharing knowledge with data-disadvantaged parties, that do not have the resources to produce high-quality data, with reduced privacy risks to the sharing parties. We make our code publicly available.- Anthology ID:
- 2023.clinicalnlp-1.3
- Volume:
- Proceedings of the 5th Clinical Natural Language Processing Workshop
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
- Venue:
- ClinicalNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 19–23
- Language:
- URL:
- https://aclanthology.org/2023.clinicalnlp-1.3
- DOI:
- 10.18653/v1/2023.clinicalnlp-1.3
- Cite (ACL):
- Paul Youssef, Jörg Schlötterer, and Christin Seifert. 2023. Privacy-Preserving Knowledge Transfer through Partial Parameter Sharing. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 19–23, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Privacy-Preserving Knowledge Transfer through Partial Parameter Sharing (Youssef et al., ClinicalNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.clinicalnlp-1.3.pdf