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

Amnesia – High-Accuracy Data Anonymization

amnesia.openaire.eu

Post reply on HN
Print view View original

51–60 of 99 posts

Re: Amnesia – High-Accuracy Data Anonymization

#51

Post by levesque »

fractionalhare wrote: post #33
levesque wrote: post #17

Earlier quoted context omitted.

What about building machine learning models that make predictions on said data? Can't just test on fake data.

This isn't my area of expertise, but I've spoken to computer vision researchers who apparently use generated data for training models for self-driving vehicle autonomy. Maybe they only use generated data for the train set and then do cross-validation on real data? I'd like to hear them chime in on this thread if any are reading here. Theoretically speaking if the generated data has the same distribution and parameter…

You could kickstart training on simulators and then do a transfer, i.e. make adjustments to your final model, on real world data. But to learn only on generated data the problem boils down to the nonparametric features you will be using to state that the generated data is similar to the real data. What is a complex enough feature to say that images are equivalent? They might be statistically equivalent according to your features, but are they really? I think this is a very hard problem, because if we did have a good answer to this question then Tesla & co. would already be training their models on perfect simulators and we wouldn't see the glitches currently found in autonomous driving applications.

Re: Amnesia – High-Accuracy Data Anonymization

#52

Post by La1n »

smarx007 wrote: post #38
privacylawthrow wrote: post #14

For data to be anonymous under GDPR, it is not enough that individuals cannot be identified from the anonymized data set. If individuals can be identified when the anonymous data set is compared with the source data set, the anonymized data is not "anonymous". For data to be truly anonymous under GDPR. there must be no other additional data that would allow for reidentification. If there is any other data that, when…

https://en.wikipedia.org/wiki/K-anonymity#Methods_for_k-anon...

k-anonymity is often only applied to "pseudoidentifiers", if you have the original dataset it'd be trivial to reverse k-anonymity applied that way. For example someone's blood pressure isn't considered an identifying variable, and would not need to be anonymised (should not too, to keep data utility high), however this would make linking against the original dataset trivial.

Re: Amnesia – High-Accuracy Data Anonymization

#53

Post by kevin_nisbet »

jacquesm wrote: post #5

Fair warning: anonymization is a hard problem. It is never easy, and you'd be surprised how many bits can leak out of what you thought was properly anonymized data. If you are using data for test purposes please use generated data, not anonymized data. This has the additional advantage that there is no potential path for live data to end up on a developers machine. added in edit: And also realize that just using a se…

Self plug, I wrote about some aspects of why this is a hard problem a couple years ago, https://goteleport.com/blog/hashing-for-anonymization/

Re: Amnesia – High-Accuracy Data Anonymization

#55

Post by La1n »

m0nster wrote: post #39
privacylawthrow wrote: post #14

For data to be anonymous under GDPR, it is not enough that individuals cannot be identified from the anonymized data set. If individuals can be identified when the anonymous data set is compared with the source data set, the anonymized data is not "anonymous". For data to be truly anonymous under GDPR. there must be no other additional data that would allow for reidentification. If there is any other data that, when…

In my experience, this is a question of interpretation (see e.g. Recital 26 and the question of what is "reasonably likely"). You can ask ten different experts, and you will get ten different opinions. Unfortunately, many aspects of the GDPR are interpreted very heterogeneously, both in individual countries and by different supervisory authorities within the countries themselves. For this reason, it is essential that…

Also this interpretation would completely block any sharing within the pharmaceutical field, where the original data is required by law to be kept for a minimum of 25 years. I personally like the definitions from UKAN, which talk about anonymous data as relating to data environments.

edit: https://msrbcel.files.wordpress.com/2020/11/adf-2nd-edition-...

Re: Amnesia – High-Accuracy Data Anonymization

#56

Post by La1n »

m0nster wrote: post #40
lwigo wrote: post #36

Use synthetic data instead? https://tonic.ai/

Also with synthetic data, there is an inherent trade-off between privacy risks and the usefulness of the data produced. However, this trade-off can be of a different nature, resulting in advantages for synthetization, for example when protecting high-dimensional data.

Are there good ways to measure the amount (original) subject level data that can be extracted from a synthetic dataset, or calculated risk of reidentification (which is nice and easy for k-anonymity (if your assumptions are valid))?

Re: Amnesia – High-Accuracy Data Anonymization

#57

Post by m0nster »

privacylawthrow wrote: post #44
m0nster wrote: post #39

Earlier quoted context omitted.

In my experience, this is a question of interpretation (see e.g. Recital 26 and the question of what is "reasonably likely"). You can ask ten different experts, and you will get ten different opinions. Unfortunately, many aspects of the GDPR are interpreted very heterogeneously, both in individual countries and by different supervisory authorities within the countries themselves. For this reason, it is essential that…

> In my experience, this is a question of interpretation (see e.g. Recital 26 and the question of what is "reasonably likely"). This is absolutely true. The hard part is that was it "reasonably likely" changes as technology changes. It's entirely possible that a data set that qualifies as anonymous today will not be anonymous in 5 years. Organizations are responsible for the data they publish. If data loses its anony…

True. For this reason, even anonymous data can usually not be shared as open data. You have to control the environment in which the data is used to control what is "reasonably likely" (see also comment by La1n above).

Re: Amnesia – High-Accuracy Data Anonymization

#58

Post by m0nster »

La1n wrote: post #55
m0nster wrote: post #39

Earlier quoted context omitted.

In my experience, this is a question of interpretation (see e.g. Recital 26 and the question of what is "reasonably likely"). You can ask ten different experts, and you will get ten different opinions. Unfortunately, many aspects of the GDPR are interpreted very heterogeneously, both in individual countries and by different supervisory authorities within the countries themselves. For this reason, it is essential that…

Also this interpretation would completely block any sharing within the pharmaceutical field, where the original data is required by law to be kept for a minimum of 25 years. I personally like the definitions from UKAN, which talk about anonymous data as relating to data environments. edit: https://msrbcel.files.wordpress.com/2020/11/adf-2nd-edition-...

Absolutely. They're doing a great job at UKAN!

Re: Amnesia – High-Accuracy Data Anonymization

#59

Post by La1n »

frankmcsherry wrote: post #4
haffi112 wrote: post #2

Do these methods provide any guarantees or is it assumed that a human reviews the output to verify that it was properly anonymized?

> Data anonymized with Amnesia are statistically guaranteed that they cannot be linked to the original data. It looks like (from other text on their site) they use variants on k-anonymity. This can prevent re-linking attacks back to the original data, but we've also known for a decade that this isn't especially strong. For example, two independent k-anonymous releases can unique identify everyone in the dataset[0]. […

However that statistical guarantee also requires your pseudoidentifiers to be picked correctly, i.e. it only holds true if you select all variables the attacker could possibly know about a subject. I think that is the hard part here, it's not something I would recommend someone doing without a lot of research and experience for highly dimensional data.
Post reply on HN