Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
- Fatemehsadat Mireshghallah ,
- Huseyin Inan ,
- Marcello Hasegawa ,
- Victor Rühle ,
- Taylor Berg-Kirkpatrick ,
- Robert Sim
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a popular choice to train models with privacy guarantees, comes with significant costs in terms of utility degradation and disparate impact on subgroups of users. In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a triplet-loss term. We compare our methods with DP through extensive evaluation. We show the advantages of our regularizers with favorable utility-privacy trade-off, faster training with the ability to tap into existing optimization approaches, and ensuring uniform treatment of under-represented subgroups.