Membership inference (safe, educational)
Measure how overfitting reveals whether a record was in the training data.
العربيةThe idea
A model is trained on synthetic data; a loss-threshold attack (Yeom et al.) is applied and its advantage over guessing measured.
Data description
Synthetic data generated in your browser from stated distributions; no real personal data.
Suggested next experiment
Concepts in this experiment
Membership advantage formula
0 means the attack is no better than guessing.
\mathrm{Adv}=\mathrm{TPR}_{\text{attack}}-\mathrm{FPR}_{\text{attack}}Membership inference (هجوم استنتاج العضوية)
Trying to tell whether a record was in a model's training data. The simplest form (Yeom et al., 2018) thresholds the loss: an overfit model has lower loss on its training examples. Risk is measured by advantage = TPR − FPR; regularisation and DP reduce it. In the lab it runs on synthetic data only.
Scientific sources for this experiment
- Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting (arXiv:1709.01604)S. Yeom, I. Giacomelli, M. Fredrikson, S. Jha (2018) — Paper
- Membership Inference Attacks against Machine Learning Models (arXiv:1610.05820)R. Shokri, M. Stronati, C. Song, V. Shmatikov (2017) — Paper
