# IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness

arXiv: https://arxiv.org/abs/2302.10896 · HTML: https://mlsanity.com/paper/2302.10896/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 9 Feb 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack](https://mlsanity.com/paper/1907.02044/) (2019)
- [Torchattacks: A PyTorch Repository for Adversarial Attacks](https://mlsanity.com/paper/2010.01950/) (2020)
- [Deep Learning based Vulnerability Detection: Are We There Yet?](https://mlsanity.com/paper/2009.07235/) (2020)
- [Are adversarial examples inevitable?](https://mlsanity.com/paper/1809.02104/) (2018)
- [The HSIC Bottleneck: Deep Learning without Back-Propagation](https://mlsanity.com/paper/1908.01580/) (2019)
- [A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples](https://mlsanity.com/paper/1608.07690/) (2016)
- [Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck](https://mlsanity.com/paper/2204.02735/) (2022)
- [Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness](https://mlsanity.com/paper/2106.02734/) (2021)

## Built on by (most cited first, 2 of 2)

- [MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness](https://mlsanity.com/paper/2312.04960/) (2023)
- [Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction](https://mlsanity.com/paper/2510.15422/) (2025)

## Abstract (arXiv)

In this paper, we propose a novel method, IB-RAR, which uses Information Bottleneck (IB) to strengthen adversarial robustness for both adversarial training and non-adversarial-trained methods. We first use the IB theory to build regularizers as learning objectives in the loss function. Then, we filter out unnecessary features of intermediate representation according to their mutual information (MI) with labels, as the network trained with IB provides easily distinguishable MI for its features. Experimental results show that our method can be naturally combined with adversarial training and provides consistently better accuracy on new adversarial examples. Our method improves the accuracy by an average of 3.07% against five adversarial attacks for the VGG16 network, trained with three adversarial training benchmarks and the CIFAR-10 dataset. In addition, our method also provides good robustness for undefended methods, such as training with cross-entropy loss only. Finally, in the absence of adversarial training, the VGG16 network trained using our method and the CIFAR-10 dataset reaches an accuracy of 35.86% against PGD examples, while using all layers reaches 25.61% accuracy.