On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models

no code implementations • 12 Mar 2021 • Benjamin Zi Hao Zhao, Aviral Agrawal, Catisha Coburn, Hassan Jameel Asghar, Raghav Bhaskar, Mohamed Ali Kaafar, Darren Webb, Peter Dickinson

In this paper, we take a closer look at another inference attack reported in literature, called attribute inference, whereby an attacker tries to infer missing attributes of a partially known record used in the training dataset by accessing the machine learning model as an API.

Attribute BIG-bench Machine Learning +1

On Inferring Training Data Attributes in Machine Learning Models

no code implementations • 28 Aug 2019 • Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Raghav Bhaskar, Mohamed Ali Kaafar

A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models.

Attribute BIG-bench Machine Learning