Subpopulation Data Poisoning Attacks

Understand

Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions.

• Poisoning attacks against machine learning induce adversarial modification of data used by a machine learning algorithm to selectively change its output when it is deployed.
• In this work, we introduce a novel data poisoning attack called a \emph{subpopulation attack}, which is particularly relevant when datasets are large and diverse.
• We design a modular framework for subpopulation attacks, instantiate it with different building blocks, and show that the attacks are effective for a variety of datasets and machine learning models.