Privacy Loss in Apple’s Implementation of Differential Privacy (2017)
arxiv.org
arxiv.org
https://machinelearning.apple.com/docs/learning-with-privacy...
I hope that they fixed the problem since this article came out but I am not so sure they are more open how they implement differential privacy.
https://machinelearning.apple.com/2017/12/06/learning-with-p...
1) "The privacy loss permitted by the system is not explained anywhere and takes significant effort to reverse-engineer. This is contrary to one of the main conceptual advantages of differential privacy – that a user can make an informed choice whether to opt-in to differentially private data collection based on the quantifiable knowledge of risk announced by the data collector."
2) "Furthermore, the lack of transparency on privacy loss opens the door for intentional or un-intentional abuse by Apple itself, e.g., by unilaterally changing either the per-datum privacy loss or the rate of privacy loss in a time period or by introducing additional BudgetKeyName(s), Apple may significantly weaken the privacy guarantees provided without anyone’s knowledge or consent."
Apple's "closed source and no documentation everything" does not help.
Sure, you might still say it isn't good enough, but I personally trust them to make the right choices for me, even if they don't inform me exactly what those choices were and what tradeoffs were made.