News for hackers. Stuff that matters.
Re:Using ‘radioactive data’ to detect if a data set was used... by lmkg on Wednesday February 05, 2020 @03:27PM (#22250657)
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

There are no comments on this comment yet.