Learning Differentially Private Recurrent Language Models — mentioned by CyanTas

Sat, 18 May 2019 05:29:09 GMT

You’re not wrong, but it does say those privacy risks can be mitigated with differential privacy. That McMahan et al. paper (which is also Google) makes the accuracy cost seem low. https://arxiv.org/abs/1710.06963

Paper and discussion history. A mention is not an endorsement.

Learning Differentially Private Recurrent Language Models — mentioned by singhrac

Sun, 25 Mar 2018 18:27:16 GMT

One problem I've found with differential privacy is that no one talks about how to set \epsilon. I've read this book, and it's quite well written and complete, but as the title says it focuses on the algorithmic foundations. This paper [1] is much better for practitioners, and actually gives very reasonable values for the privacy guarantee (e.g., (1.2, 1e-9)), and builds on this great paper: [2]. Worth a read if you train neural networks. [1]: https://arxiv.org/pdf/1710.06963.pdf [2]: https://arxiv.org/pdf/1607.00133.pdf

Paper and discussion history. A mention is not an endorsement.

Learning Differentially Private Recurrent Language Models · HackerPapers discussions

Learning Differentially Private Recurrent Language Models — mentioned by CyanTas

Learning Differentially Private Recurrent Language Models — mentioned by singhrac