Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How Cambridge Analytica’s Facebook targeting model really worked

niemanlab.org

Post reply on HN
Print view View original

81–90 of 210 posts

Re: How Cambridge Analytica’s Facebook targeting model really worked

#81

Post by MattyRad »

ikeyany wrote: post #40
emodendroket wrote: post #19

I am really puzzled by the Cambridge Analytica scandal. It's not particularly savory, but is there something happening here that it wasn't basically already known about how Facebook worked? By the protests of their own executive, the system was working as designed, and at worst Cambridge Analytica misled them about how they intended to use the data, right? There was no actual security breach here, as far as I can und…

Who said anything about a security breach? Most of the controversy has been about the company influencing elections using data scraped from people (and their friends) unaware of what the data was being used for.

The degree to which it influenced the election is questionable. Despite all the headlines, I haven't yet seen any convincing analysis of the impact of facebook on the election (I'm not sure how one would even go about doing so). So far it seems like it's just a convenient vehicle for people that dislike the outcome of the election to express indignation.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#82

Post by vcdimension »

This is the standard way of analysing this kind of data, and I'd be very surprised if the Obama campaign didn't use the same or very similar methods with the facebook data they obtained. The only difference is that Cambridge Analytica managed to obtain much more data over a wider demographic.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#83

Post by darawk »

anf wrote: post #80
darawk wrote: post #75

Earlier quoted context omitted.

If they kept information like that, then yes that would be an invasion of privacy. But that sort of information is almost certainly not encoded in an ML model trained on 50 million people's data.

How do you know what CA trained on, or what's possible? Do you have qualifications in ML?

I know what they trained on because it's been reported on. They got around 50 million people's FB profiles, and a smaller subset's (300k, I think) personality test results.

I use ML models every day in my work, and understand how they function. It is true that individuals information is probabilistically encoded into the parameters of the model. However, if the model is any good, the people they trained on's information is encoded only a bit more than that of the entire population.

There is sort of a privacy issue in the following sense: The models they've built have learned relationships between preferences and personalities that they wouldn't otherwise have been able to learn. But these relationships are abstract. They are not tethered to any particular, identifiable individual.

A reasonable argument can be made that those learned relationships are, in a sense, stolen property. And I think arguments along those lines are interesting things that we'll have to explore as this sort of thing becomes more common. But the idea that this model invades individuals privacy just isn't really true.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#84

Post by stochastic_monk »

darawk wrote: post #68
etiam wrote: post #41

Spoiler warning. Article punchline ahead. "The whole point of a dimension reduction model is to mathematically represent the data in simpler form. It’s as if Cambridge Analytica took a very high-resolution photograph, resized it to be smaller, and then deleted the original. The photo still exists — and as long as Cambridge Analytica’s models exist, the data effectively does too." That's an eloquent piece of explanati…

> when strictly speaking the raw data has indeed been deleted after being used to create a derivative work that can for all important purposes be used to recreate the original? To be precise, you almost certainly cannot use this data to recreate anything remotely resembling the original dataset. This type of dimensionality reduction would throw away enormous volumes of data. There is no meaningful sense in which you…

That's only accurate in the sense that because an LSTM's hidden layer is much smaller in dimension than the data on which it is trained, there is less information in it.

However, it concisely represents a manifold in a much larger dimensional space and effectively captures most of the information in it.

It may be (and is) lossy, but don't underestimate the expressive power of a deep neural network.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#85

Post by spydum »

anf wrote: post #71
darawk wrote: post #68

Earlier quoted context omitted.

> when strictly speaking the raw data has indeed been deleted after being used to create a derivative work that can for all important purposes be used to recreate the original? To be precise, you almost certainly cannot use this data to recreate anything remotely resembling the original dataset. This type of dimensionality reduction would throw away enormous volumes of data. There is no meaningful sense in which you…

> It's arguable whether they should be allowed to keep those insights, but there's no privacy risk there really. So if Google has distilled someone's emails over the years into "closeted homosexual with a deeply repressed leather fetish", that's not an invasion of their privacy as long as they throw away the source materials?

As long as they retain no data which could specifically identify the original person, yes. There is nothing wrong with building segmentation models as long as they aren't specific enough to identify a specific person.

My concern would be, how granular is too granular? What if we added "and live in zip code 12355 and is registered Green Party"? This now gets eerily specific, and might be sufficient to identify an individual.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#86

Post by wybiral »

stochastic_monk wrote: post #84
darawk wrote: post #68

Earlier quoted context omitted.

> when strictly speaking the raw data has indeed been deleted after being used to create a derivative work that can for all important purposes be used to recreate the original? To be precise, you almost certainly cannot use this data to recreate anything remotely resembling the original dataset. This type of dimensionality reduction would throw away enormous volumes of data. There is no meaningful sense in which you…

That's only accurate in the sense that because an LSTM's hidden layer is much smaller in dimension than the data on which it is trained, there is less information in it. However, it concisely represents a manifold in a much larger dimensional space and effectively captures most of the information in it. It may be (and is) lossy, but don't underestimate the expressive power of a deep neural network.

Especially when the dataset probably isn't that high in entropy. Something like PCA can drop the dimensionality by significant amounts as long as the data has enough clear signals in it.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#87

Post by pflanze »

darawk wrote: post #83
anf wrote: post #80

Earlier quoted context omitted.

How do you know what CA trained on, or what's possible? Do you have qualifications in ML?

I know what they trained on because it's been reported on. They got around 50 million people's FB profiles, and a smaller subset's (300k, I think) personality test results. I use ML models every day in my work, and understand how they function. It is true that individuals information is probabilistically encoded into the parameters of the model. However, if the model is any good, the people they trained on's informat…

But if the resulting model doesn't contain information about individuals, how does this help targeting individuals for the campaign?

Edit: is it that the model is then applied to only strictly public data about the person? If so I guess the interesting question then becomes whether the model is definitely not anything near overfitting (i.e. containing enough information to match a person's public data directly since it was trained on it (amongst other data))? (I'm not an ML developer.)

Edit 2: also, going with your comparison with the "20 most representative pixels", it seems interesting then that 'this much' (although not exactly sure how much) information can be inferred from a public profile when just also knowing enough about the whole Facebook population. OK, so perhaps a human would be able to infer about as much, but doesn't scale, and that's why the model becomes valuable?

Re: How Cambridge Analytica’s Facebook targeting model really worked

#88

Post by salty_biscuits »

stochastic_monk wrote: post #84
darawk wrote: post #68

Earlier quoted context omitted.

> when strictly speaking the raw data has indeed been deleted after being used to create a derivative work that can for all important purposes be used to recreate the original? To be precise, you almost certainly cannot use this data to recreate anything remotely resembling the original dataset. This type of dimensionality reduction would throw away enormous volumes of data. There is no meaningful sense in which you…

That's only accurate in the sense that because an LSTM's hidden layer is much smaller in dimension than the data on which it is trained, there is less information in it. However, it concisely represents a manifold in a much larger dimensional space and effectively captures most of the information in it. It may be (and is) lossy, but don't underestimate the expressive power of a deep neural network.

Only if the "true" data actually lives in a lower dimensional manifold and the data acurrately can encode it with low noise. I doubt anyone can tell who you will vote for depending on which cat videos you liked, no matter how magic your regressor.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#89

Post by wybiral »

darawk wrote: post #76
berkay wrote: post #72

Earlier quoted context omitted.

Analogy does not work here and is misleading. You cannot do much if anything with 20 most representative pixels (if there is such a thing) but you can infer highly valuable characteristics about the person. Yes, you cannot recreate the original data but what you end up is potentially much worse (sensitive/private) than the original data.

That's not really true, and is kind of a fundamental misunderstanding of how these things work.

Unless the data is completely random it's not crazy to say that the data can be reconstructed from a reduced version.

If you have a million points that largely fall on a 3-dimensional line and you project that into 2 dimensions, you can easily recover that lost dimension with losses relative to the deviation. And that loss may not even matter depending on the kinds of data and margins of error you're working in.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#90

Post by darawk »

wybiral wrote: post #89
darawk wrote: post #76

Earlier quoted context omitted.

That's not really true, and is kind of a fundamental misunderstanding of how these things work.

Unless the data is completely random it's not crazy to say that the data can be reconstructed from a reduced version. If you have a million points that largely fall on a 3-dimensional line and you project that into 2 dimensions, you can easily recover that lost dimension with losses relative to the deviation. And that loss may not even matter depending on the kinds of data and margins of error you're working in.

Except that that toy example bears no resemblance to the actual situation.
Post reply on HN