SNAP: Efficient Extraction of Private Properties with Poisoning. (arXiv:2208.12348v1 [cs.LG])

Property inference attacks allow an adversary to extract global properties of
the training dataset from a machine learning model. Such attacks have privacy
implications for data owners who share their datasets to train machine learning
models. Several existing approaches for property inference attacks against deep
neural networks have been proposed, but they all rely on the attacker training
a large number of shadow models, which induces large computational overhead.

In this paper, we consider the setting of property inference attacks …

lg poisoning snap