Just to clear it up, it doesn't learn by creating data on its own, but rather has other algorithms spoonfeeding it information so that the personal data doesn't ever reach the student AI.
This seems to be more about reducing the risk of reverse engineering the training data of a machine learned system, which could expose sensitive information.
Without any special countermeasures, training a model on medical patient data and then releasing the model's parameters or even just making it possible for others to run the model on inputs they supply might allow someone to partially reconstruct the patient data.
This is a somewhat separate issue from whether the engineers building this system have access to the training data. You can achieve that by writing your training script and then running it in an environment that you don't personally have read access to.
Being a pessimist about school, as it wasn't fun for me or fit my learning style, I found myself thinking that we were going to only make AI as stupid as we are with this method.
On the real side, however, I think anyway in which we can keep people and their information safe in the face of progress are paths we should absolutely take.
11 comments
[ 3.2 ms ] story [ 18.6 ms ] threadhttps://en.wikipedia.org/wiki/De-anonymization
Without any special countermeasures, training a model on medical patient data and then releasing the model's parameters or even just making it possible for others to run the model on inputs they supply might allow someone to partially reconstruct the patient data.
This is a somewhat separate issue from whether the engineers building this system have access to the training data. You can achieve that by writing your training script and then running it in an environment that you don't personally have read access to.
On the real side, however, I think anyway in which we can keep people and their information safe in the face of progress are paths we should absolutely take.