Selective Differential Privacy for Language Modeling. (arXiv:2108.12944v3 [cs.CL] UPDATED)

With the increasing applications of language models, it has become crucial to
protect these models from leaking private information. Previous work has
attempted to tackle this challenge by training RNN-based language models with
differential privacy guarantees. However, applying classical differential
privacy to language models leads to poor model performance as the underlying
privacy notion is over-pessimistic and provides undifferentiated protection for
all tokens in the data. Given that the private information in natural language
is sparse (for example, the bulk …

differential privacy language modeling privacy