Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Not on the map. Why?
Abstract (arXiv)
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Error-Correcting Output Codes (ECOC) ensembles through architectural improvements and ensemble diversity promotion. We perform a comprehensive robustness assessment against adaptive attacks and investigate the relationship between ensemble diversity and robustness. Our results demonstrate the benefits of ECOC ensembles for adversarial robustness compared to regular ensembles of convolutional neural networks (CNNs) and show why the robustness of previous implementations is limited. We also propose an adversarial training method specific to ECOC ensembles that allows to further improve robustness to adaptive attacks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 4 Mar 2023.
Builds on
17 of 23 references.
References · 17
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
- 2019On Evaluating Adversarial Robustnesscited by 442
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
- 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
- 2020Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspectivecited by 35
- 2017Adversarial Example Defenses: Ensembles of Weak Defenses are not Strongcited by 32
5 more
- 2020EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attackscited by 28
- 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
- 2019Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networkscited by 11
- 2020Integer Programming-based Error-Correcting Output Code Design for Robust Classificationcited by 2
- 2020Deep Convolutional Neural Network Ensembles using ECOCcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.