# Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness

Source: [Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness](<https://www.sota2.com/research/paper/68fa73561e209131cea5bede>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:48:16.237Z

Authors: Jieren Deng, Hanbin Hong, Aaron Palmer, Xin Zhou, Jinbo Bi, Kaleel Mahmood, Yuan Hong, Derek Aguiar

Published: 2024-05-25T03:18:52.000Z

## Abstract

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l\_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with Gaussian noise and adversarial training, require expensive training procedures that tune large models for different Gaussian noise levels and thus cannot leverage high-performance pre-trained neural networks. In this work, we introduce a novel certifying adapters framework (CAF) that enables and enhances the certification of classifier adversarial robustness. Our approach makes few assumptions about the underlying training algorithm or feature extractor and is thus broadly applicable to different feature extractor architectures (e.g., convolutional neural networks or vision transformers) and smoothing algorithms. We show that CAF (a) enables certification in uncertified models pre-trained on clean datasets and (b) substantially improves the performance of certified classifiers via randomized smoothing and SmoothAdv at multiple radii in CIFAR-10 and ImageNet. We demonstrate that CAF achieves improved certified accuracies when compared to methods based on random or denoised smoothing, and that CAF is insensitive to certifying adapter hyperparameters. Finally, we show that an ensemble of adapters enables a single pre-trained feature extractor to defend against a range of noise perturbation scales.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.16036>)

[PDF](<https://arxiv.org/pdf/2405.16036.pdf>)
