Mitigating Unintended Memorization in Language Models via Alternating Teaching

Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. We employ a teacher-student framework and propose a novel approach called alternating teaching to mitigate unintended mem...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Liu, Zhe, Zhang, Xuedong, Peng, Fuchun
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 13.10.2022
Subjects
Privacy
Teachers
Training
Online AccessGet full text

Cover

More Information
Summary:Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. We employ a teacher-student framework and propose a novel approach called alternating teaching to mitigate unintended memorization in sequential modeling. In our method, multiple teachers are trained on disjoint training sets whose privacy one wishes to protect, and teachers' predictions supervise the training of a student model in an alternating manner at each time step. Experiments on LibriSpeech datasets show that the proposed method achieves superior privacy-preserving results than other counterparts. In comparison with no prevention for unintended memorization, the overall utility loss is small when training records are sufficient.
ISSN:2331-8422