What is Differential Privacy?
blog.cryptographyengineering.com
What is Differential Privacy?
1–10 of 108 posts
Re: What is Differential Privacy?
#2Re: What is Differential Privacy?
#3Uh, the graph is just showing you get an increased 25% estimated risk of mortality from Warfarin, nothing close to "killing patients". Complete exageration, since the mortality baseline is probably very low in the first place.
Re: What is Differential Privacy?
#4I have to admit, I'm really starting to like the direction that Apple is heading despite being previously disenchanted. I only wish that they would go ahead and put everything under a free software license, since they're in the business of selling hardware that's coincidentally bundled with their software.
The recent WWDC obviously shows a big shift towards AI and ML applications within the company. Some things are possible on the device, but many neural nets just cannot be served from an iPhone reasonably. Hence, the move towards more data collection. I really wish they give out more information here. Until then, I'm not sure how much they are actually collecting after their realization that they do need the data to do AI well.
Re: What is Differential Privacy?
#5I have to admit, I'm really starting to like the direction that Apple is heading despite being previously disenchanted. I only wish that they would go ahead and put everything under a free software license, since they're in the business of selling hardware that's coincidentally bundled with their software.
Re: What is Differential Privacy?
#6I have to admit, I'm really starting to like the direction that Apple is heading despite being previously disenchanted. I only wish that they would go ahead and put everything under a free software license, since they're in the business of selling hardware that's coincidentally bundled with their software.
To paint another viewpoint, Apple initially went all gung ho about privacy and wanted to make not collecting data a big play (and fairly so, full respect to them). The recent WWDC obviously shows a big shift towards AI and ML applications within the company. Some things are possible on the device, but many neural nets just cannot be served from an iPhone reasonably. Hence, the move towards more data collection. I rea…
Re: What is Differential Privacy?
#7I have to admit, I'm really starting to like the direction that Apple is heading despite being previously disenchanted. I only wish that they would go ahead and put everything under a free software license, since they're in the business of selling hardware that's coincidentally bundled with their software.
That's never going to happen. Apple sells a 'User Experience' not just hardware - having a complete and mostly closed product is an inevitable consequence of the former - and the number of Linux users that would buy a Macbook isn't a large enough part of the market for them to worry about.
With that said I've had a Macbook Pro and it was pretty much a better piece of hardware (at least as far as build quality) than any other notebook I've used.
Re: What is Differential Privacy?
#8> On the other hand, when the budget was reduced to a level that achieved meaningful privacy, the "noise-ridden" model had a tendency to kill its "patients". Uh, the graph is just showing you get an increased 25% estimated risk of mortality from Warfarin, nothing close to "killing patients". Complete exageration, since the mortality baseline is probably very low in the first place.
Re: What is Differential Privacy?
#9Earlier quoted context omitted.
To paint another viewpoint, Apple initially went all gung ho about privacy and wanted to make not collecting data a big play (and fairly so, full respect to them). The recent WWDC obviously shows a big shift towards AI and ML applications within the company. Some things are possible on the device, but many neural nets just cannot be served from an iPhone reasonably. Hence, the move towards more data collection. I rea…
They talked a bit more about differential privacy in the State of the Union. Basically, they hash the data and add noise. By collecting data from a bunch of people that noise gets averaged out. They also limit the amount of samples (over a relatively short period of time) they can get from a single person so they won't be able to identify them.
Re: What is Differential Privacy?
#10> On the other hand, when the budget was reduced to a level that achieved meaningful privacy, the "noise-ridden" model had a tendency to kill its "patients". Uh, the graph is just showing you get an increased 25% estimated risk of mortality from Warfarin, nothing close to "killing patients". Complete exageration, since the mortality baseline is probably very low in the first place.
Good luck selling that to doctors. People who are trained to cut open a patient aren't receptive to hypothetical harms and imaginary "budgets". Consider the fact that cause of death records are public. The usual perception of privacy by theory and security researchers and norms practiced in healthcare differ enormously.