Membership Inference Attacks on Machine Learning: A Survey

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. MIAs on ML models can directly lead to a privacy breach. For example, via identifying the fact that a clinical record that has been used to train a model associated with a certain disease, an attacker can infer that the owner of the clinical record has the disease with a high chance. In recent years, MIAs have been shown to be effective on various ML models,…

• NS
  National Science Foundation

  Awards: 1909323, 1763325, III-1763325, III-1909323, III-2106758, and SaTC-1930941, 2106758, III-2106758, III-1763325, III-1909323, SaTC-1930941, 1930941
• AG
  Australian Government

  Award: DE210101458