Black-Box Audits for Group Distribution Shifts
Juarez, Marc, Yeom, Samuel, Fredrikson, Matt
–arXiv.org Artificial Intelligence
When a model informs decisions about people, distribution shifts can create undue disparities. However, it is hard for external entities to check for distribution shift, as the model and its training set are often proprietary. In this paper, we introduce and study a black-box auditing method to detect cases of distribution shift that lead to a performance disparity of the model across demographic groups. By extending techniques used in membership and property inference attacks -- which are designed to expose private information from learned models -- we demonstrate that an external auditor can gain the information needed to identify these distribution shifts solely by querying the model. Our experimental results on real-world datasets show that this approach is effective, achieving 80--100% AUC-ROC in detecting shifts involving the underrepresentation of a demographic group in the training set. Researchers and investigative journalists can use our tools to perform non-collaborative audits of proprietary models and expose cases of underrepresentation in the training datasets.
arXiv.org Artificial Intelligence
Sep-8-2022
- Country:
- North America > United States
- California (0.14)
- Michigan (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- New York > New York County
- New York City (0.04)
- North America > United States
- Genre:
- Research Report
- New Finding (1.00)
- Experimental Study (1.00)
- Research Report
- Industry:
- Information Technology > Security & Privacy (0.93)
- Transportation > Air (0.61)
- Technology: