Provably Robust Conformal Prediction with Improved Efficiency

TL;DR

This paper introduces RSCP+ and two new methods, PTT and RCT, to improve the efficiency and robustness of conformal prediction under adversarial conditions, achieving significant reductions in uncertainty set size while maintaining coverage guarantees.

Contribution

The paper proposes RSCP+ for provable robustness guarantees and introduces PTT and RCT methods to reduce prediction set size with minimal computational overhead.

Findings

RSCP+ fixes flaws in previous robustness guarantees.

PTT and RCT significantly reduce prediction set size.

Methods achieve up to 16.9x efficiency improvement on ImageNet.

Abstract

Conformal prediction is a powerful tool to generate uncertainty sets with guaranteed coverage using any predictive model, under the assumption that the training and test data are i.i.d.. Recently, it has been shown that adversarial examples are able to manipulate conformal methods to construct prediction sets with invalid coverage rates, as the i.i.d. assumption is violated. To address this issue, a recent work, Randomized Smoothed Conformal Prediction (RSCP), was first proposed to certify the robustness of conformal prediction methods to adversarial noise. However, RSCP has two major limitations: (i) its robustness guarantee is flawed when used in practice and (ii) it tends to produce large uncertainty sets. To address these limitations, we first propose a novel framework called RSCP+ to provide provable robustness guarantee in evaluation, which fixes the issues in the original RSCP method. Next, we propose two novel methods, Post-Training Transformation (PTT) and Robust Conformal Training (RCT), to effectively reduce prediction set size with little computation overhead. Experimental results in CIFAR10, CIFAR100, and ImageNet suggest the baseline method only yields trivial predictions including full label set, while our methods could boost the efficiency by up to $4.36\times$, $5.46\times$, and $16.9\times$ respectively and provide practical robustness guarantee. Our codes are available at https://github.com/Trustworthy-ML-Lab/Provably-Robust-Conformal-Prediction.