Robust Yet Efficient Conformal Prediction Sets

Soroush H. Zargarbashi; Mohammad Sadegh Akhondzadeh; Aleksandar Bojchevski

ICML 2024poster7 citations

Robust Yet Efficient Conformal Prediction Sets

Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski

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).

BibTeX

@inproceedings{
zargarbashi2024robust,
title={Robust Yet Efficient Conformal Prediction Sets},
author={Soroush H. Zargarbashi and Mohammad Sadegh Akhondzadeh and Aleksandar Bojchevski},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=MrNq6rbcUi}
}