Adversarial Training for Privacy-Preserving Deep Learning Model Distribution

Conference · Sun Dec 01 00:00:00 EST 2019

DOI:https://doi.org/10.1109/BigData47090.2019.9006131· OSTI ID:1606810

Alawad, Mohammed  ^[1]; Gao, Shang ^[1]; Wu, Xiao-Cheng ^[2]; Durbin, Eric B. ^[3]; Coyle, Linda ^[4]; Penberthy, Lynne ^[4]; Tourassi, Georgia  ^[1]

---

1. ORNL
2. LSUHSC-Louisiana Tumor Registry
3. University of Kentucky
4. National Cancer Institute, Bethesda, MD

Collaboration among cancer registries is essential to develop accurate, robust, and generalizable deep learning models for automated information extraction from cancer pathology reports. Sharing data presents a serious privacy issue, especially in biomedical research and healthcare delivery domains. Distributing pretrained deep learning (DL) models has been proposed to avoid critical data sharing. However, there is growing recognition that collaboration among clinical institutes through DL model distribution exposes new security and privacy vulnerabilities. These vulnerabilities increase in natural language processing (NLP) applications, in which the dataset vocabulary with word vector representations needs to be associated with the other model parameters. In this paper, we propose a novel privacy-preserving DL model distribution across cancer registries for information extraction from cancer pathology reports with privacy and confidentiality considerations. The proposed approach exploits the adversarial training framework to distinguish private features from shared features among different datasets. It only shares registry-invariant model parameters, without sharing raw data nor registry-specific model parameters among cancer registries. Thus, it protects both the data and the trained model simultaneously. We compare our proposed approach to single-registry models, and a model trained on centrally hosted data from different cancer registries. The results show that the proposed approach significantly outperforms the single-registry models and achieves statistically indistinguishable micro and macro F1-score as compared to the centralized model.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1606810
• Resource Relation: Conference: 2019 IEEE International Conference on Big Data (IEEE BigData 2019) - Los Angeles, California, United States of America - 12/9/2019 5:00:00 AM-12/12/2019 5:00:00 AM
• Country of Publication: United States
• Language: English