Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness
Not on the map. Why?
Abstract (arXiv)
Robustness of deep neural networks (DNNs) to malicious perturbations is a hot topic in trustworthy AI. Existing techniques obtain robust models given fixed datasets, either by modifying model structures, or by optimizing the process of inference or training. While significant improvements have been made, the possibility of constructing a high-quality dataset for model robustness remain unexplored. Follow the campaign of data-centric AI launched by Andrew Ng, we propose a novel algorithm for dataset enhancement that works well for many existing DNN models to improve robustness. Transferable adversarial examples and 14 kinds of common corruptions are included in our optimized dataset. In the data-centric robust learning competition hosted by Alibaba Group and Tsinghua University, our algorithm came third out of more than 3000 competitors in the first stage while we ranked fourth in the second stage. Our code is available at urlhttps://github.com/hncszyq/tianchichallenge.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 27 references that are in the map. First posted on arXiv 10 Mar 2022.
Builds on
23 of 27 references.
References · 23
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2016Wide Residual Networkscited by 3,057
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
11 more
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
- 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
- 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
- 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
- 2021Online Adversarial Purification based on Self-Supervisioncited by 45
- 2020DSRNA: Differentiable Search of Robust Neural Architecturescited by 27
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1.
2 papers.