# CEB Improves Model Robustness

arXiv: https://arxiv.org/abs/2002.05380 · HTML: https://mlsanity.com/paper/2002.05380/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2020.

## Built on by (most cited first, 14 of 14)

- [How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?](https://mlsanity.com/paper/2112.11668/) (2021)
- [DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation](https://mlsanity.com/paper/2101.05544/) (2021)
- [Compressive Visual Representations](https://mlsanity.com/paper/2109.12909/) (2021)
- [Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration](https://mlsanity.com/paper/2103.12300/) (2021)
- [An Empirical Investigation of Representation Learning for Imitation](https://mlsanity.com/paper/2205.07886/) (2022)
- [Balancing Multimodal Training Through Game-Theoretic Regularization](https://mlsanity.com/paper/2411.07335/) (2024)
- [A Closer Look at the Adversarial Robustness of Information Bottleneck Models](https://mlsanity.com/paper/2107.05712/) (2021)
- [α-TCVAE: On the relationship between Disentanglement and Diversity](https://mlsanity.com/paper/2411.00588/) (2024)
- [Gated Information Bottleneck for Generalization in Sequential Environments](https://mlsanity.com/paper/2110.06057/) (2021)
- [Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network](https://mlsanity.com/paper/2210.14229/) (2022)
- [Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck](https://mlsanity.com/paper/2203.02592/) (2022)
- [TC-VAE: Uncovering Out-of-Distribution Data Generative Factors](https://mlsanity.com/paper/2304.04103/) (2023)
- [Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals](https://mlsanity.com/paper/2403.16176/) (2024)
- [TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks](https://mlsanity.com/paper/2211.13902/) (2022)

## Abstract (arXiv)

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.