# CEB Improves Model Robustness

Source: [CEB Improves Model Robustness](<https://www.sota2.com/research/paper/68fa689c1e209131cea1d050>)

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

Data updated: 2025-10-28T13:56:45.054Z

Authors: Ian Fischer, Alexander A. Alemi

Published: 2020-02-13T07:49:22.000Z

## Abstract

We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve model robustness. CEB is an easy strategy to implement and works in tandem with data augmentation procedures. We report results of a large scale adversarial robustness study on CIFAR-10, as well as the ImageNet-C Common Corruptions Benchmark, ImageNet-A, and PGD attacks.

## 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/2002.05380>)

[PDF](<https://arxiv.org/pdf/2002.05380.pdf>)