Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network
Not on the map. Why?
Abstract (arXiv)
The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of adversarial robustness. In this paper, we incorporate the causal inference into the IB framework to alleviate such a problem. Specifically, we divide the features obtained by the IB method into robust features (content information) and non-robust features (style information) via the instrumental variables to estimate the causal effects. With the utilization of such a framework, the influence of non-robust features could be mitigated to strengthen the adversarial robustness. We make an analysis of the effectiveness of our proposed method. The extensive experiments in MNIST, FashionMNIST, and CIFAR-10 show that our method exhibits the considerable robustness against multiple adversarial attacks. Our code would be released.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 46 of its 70 references that are in the map. First posted on arXiv 25 Oct 2022.
Builds on
46 of 70 references.
References · 46
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2013Intriguing properties of neural networkscited by 5,114
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016Wide Residual Networkscited by 3,057
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
34 more
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2016Deep Variational Information Bottleneckcited by 915
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2017Counterfactual Fairnesscited by 802
- 2015Deep Learning and the Information Bottleneck Principlecited by 793
- 2016Universal adversarial perturbationscited by 774
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
- 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2019On Evaluating Adversarial Robustnesscited by 442
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
- 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
- 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
- 2016Information Dropout: Learning Optimal Representations Through Noisy Computationcited by 131
- 2017Learning Independent Causal Mechanismscited by 104
- 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
- 2020The Conditional Entropy Bottleneckcited by 75
- 2020A Causal View on Robustness of Neural Networkscited by 53
- 2017Defense against Universal Adversarial Perturbationscited by 48
- 2019Theoretical evidence for adversarial robustness through randomizationcited by 33
- 2022Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneckcited by 30
- 2020Diversity inducing Information Bottleneck in Model Ensemblescited by 27
- 2020Disentangled Information Bottleneckcited by 24
- 2017Generative Adversarial Trainer: Defense to Adversarial Perturbations with GANcited by 20
- 2019Information bottleneck through variational glassescited by 19
- 2020CEB Improves Model Robustnesscited by 14
- 2021Adversarial Visual Robustness by Causal Interventioncited by 13
- 2016Learning Adversary-Resistant Deep Neural Networkscited by 9
- 2021A Closer Look at the Adversarial Robustness of Information Bottleneck Modelscited by 4
- 2020Stable Prediction via Leveraging Seed Variablecited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.
3 papers.