mlsanityData to 7 Oct 2026

A Closer Look at the Adversarial Robustness of Information Bottleneck Models

arXiv 2107.05712 ↗First posted 12 Jul 2021cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks can improve upon adversarial training. Our evaluation under a diverse range of white-box l∞ attacks suggests that information bottlenecks alone are not a strong defense strategy, and that previous results were likely influenced by gradient obfuscation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 12 Jul 2021.

Builds on

18 of 26 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  7. 2016Deep Variational Information Bottleneckcited by 915
  8. 2018Robustness May Be at Odds with Accuracycited by 873
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  10. 2019On Evaluating Adversarial Robustnesscited by 442
  11. 2018Robustness via curvature regularization, and vice versacited by 174
  12. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
6 more
  1. 2019Adversarial Robustness through Local Linearizationcited by 146
  2. 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
  3. 2020Towards a Theoretical Understanding of the Robustness of Variational Autoencoderscited by 17
  4. 2020Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learningcited by 16
  5. 2020CEB Improves Model Robustnesscited by 14
  6. 2021Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attackscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2022Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Networkcited by 3
  2. 2022Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Informationcited by 0
  3. 2024Variational and Explanatory Neural Networks for Encoding Cancer Profiles and Predicting Drug Responsescited by 0
  4. 2026When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layerscited by 0