Deep Learning with Differential Privacy · HackerPapers discussions

Deep Learning with Differential Privacy — mentioned by maximeago

Thu, 17 Mar 2022 08:02:22 GMT

If the model training is designed to profile just one user, no, the model won't work by design. What you describe is an attack on the privacy of that user and we do want to make sure they fail. The way differential privacy works with machine learning is that it guarantees that one given record cannot have a significant impact on the weights of the models and therefore on its performance. In the particular case of SGD-based models, the guarantee holds for every step of the descent. A good place to start on the topic is Abadi 2016 (https://arxiv.org/pdf/1607.00133.pdf). What is important in the…

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

Deep Learning with Differential Privacy — 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.

Deep Learning with Differential Privacy — mentioned by chubot

Sat, 08 Oct 2016 03:57:15 GMT

I admit I geeked out and calculated this a couple months ago, after I was credited on my first academic paper (my career is in programming) If you count video games, I have a Bacon number of 3 because I was credited on Tiger Woods 2003-2005 with an artist named Sylvain Doreau, who is credited on Shrek. John Lithgow was in Shrek and in Footloose with Kevin Bacon. My former coworker Li Zhang has an Erdos number of 2 and we worked together on this paper: https://arxiv.org/abs/1607.00133 (with him doing a lot more work than me). So putting that together is an Erdos-Bacon number of 3 + 3 = 6.

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