CEB Improves Model Robustness
Not on the map. Why?
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.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Feb 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 4; 2023: 1; 2024: 3.
14 papers.
Sort:
By area:
- 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
- 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
- 2021Compressive Visual Representationscited by 41
- 2021Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Explorationcited by 15
- 2022An Empirical Investigation of Representation Learning for Imitationcited by 15
- 2024Balancing Multimodal Training Through Game-Theoretic Regularizationcited by 13
- 2021A Closer Look at the Adversarial Robustness of Information Bottleneck Modelscited by 4
- 2024α-TCVAE: On the relationship between Disentanglement and Diversitycited by 4
- 2021Gated Information Bottleneck for Generalization in Sequential Environmentscited by 3
- 2022Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Networkcited by 3
- 2022Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneckcited by 1
- 2023TC-VAE: Uncovering Out-of-Distribution Data Generative Factorscited by 1
- 2024Balancing Multimodal Training Through Game-Theoretic Regularization11 Nov 2024
- 2024α-TCVAE: On the relationship between Disentanglement and Diversity1 Nov 2024
- 2024Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals24 Mar 2024
- 2023TC-VAE: Uncovering Out-of-Distribution Data Generative Factors8 Apr 2023
- 2022TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks25 Nov 2022
- 2022Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network25 Oct 2022
- 2022An Empirical Investigation of Representation Learning for Imitation16 May 2022
- 2022Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck4 Mar 2022
- 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?22 Dec 2021
- 2021Gated Information Bottleneck for Generalization in Sequential Environments12 Oct 2021
- 2021Compressive Visual Representations27 Sep 2021
- 2021A Closer Look at the Adversarial Robustness of Information Bottleneck Models12 Jul 2021
- 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
- 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
- 2021Compressive Visual Representationscited by 41
- 2021Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Explorationcited by 15
- 2024Balancing Multimodal Training Through Game-Theoretic Regularizationcited by 13
- 2021A Closer Look at the Adversarial Robustness of Information Bottleneck Modelscited by 4
- 2024α-TCVAE: On the relationship between Disentanglement and Diversitycited by 4
- 2021Gated Information Bottleneck for Generalization in Sequential Environmentscited by 3
- 2022Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Networkcited by 3
- 2022Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneckcited by 1
- 2023TC-VAE: Uncovering Out-of-Distribution Data Generative Factorscited by 1
- 2024Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signalscited by 1
12 most cited of 13 All 13 (JSON)
- 2024Balancing Multimodal Training Through Game-Theoretic Regularization11 Nov 2024
- 2024α-TCVAE: On the relationship between Disentanglement and Diversity1 Nov 2024
- 2024Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals24 Mar 2024
- 2023TC-VAE: Uncovering Out-of-Distribution Data Generative Factors8 Apr 2023
- 2022TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks25 Nov 2022
- 2022Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network25 Oct 2022
- 2022Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck4 Mar 2022
- 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?22 Dec 2021
- 2021Gated Information Bottleneck for Generalization in Sequential Environments12 Oct 2021
- 2021Compressive Visual Representations27 Sep 2021
- 2021A Closer Look at the Adversarial Robustness of Information Bottleneck Models12 Jul 2021
- 2021Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration23 Mar 2021
12 newest of 13 All 13 (JSON)