|
|
|
|
|
|
by lmkg
2320 days ago
|
|
|
This is definitely true. In fact, this can be exploited to extract sensitive/private attributes about the training data from the learned models. This may become an issue for, e.g., AI in healthcare. "Overlearning Reveals Sensitive Attributes": https://arxiv.org/abs/1905.11742 |
|
|