Robust Yet Efficient Conformal Prediction Sets
This addresses security concerns in conformal prediction for users needing reliable uncertainty estimates under adversarial conditions.
The paper tackles the vulnerability of conformal prediction to adversarial attacks on test and calibration data, deriving provably robust prediction sets with tighter bounds that improve efficiency.
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).