Emergent Mind
Robust Yet Efficient Conformal Prediction Sets
(2407.09165)
Published Jul 12, 2024
in
cs.LG
and
cs.AI
Abstract
Conformal prediction (CP) can convert any model's output into prediction sets guaranteed to include the true label with any user-specified probability. However, same as the model itself, CP is vulnerable to adversarial test examples (evasion) and perturbed calibration data (poisoning). We derive provably robust sets by bounding the worst-case change in conformity scores. Our tighter bounds lead to more efficient sets. We cover both continuous and discrete (sparse) data and our guarantees work both for evasion and poisoning attacks (on both features and labels).
We're analyzing this paper now.
Try reloading the page in a minute or two to see an analysis.