Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection
Not on the map. Why?
Abstract (arXiv)
As the COVID-19 pandemic puts pressure on healthcare systems worldwide, the computed tomography image based AI diagnostic system has become a sustainable solution for early diagnosis. However, the model-wise vulnerability under adversarial perturbation hinders its deployment in practical situation. The existing adversarial training strategies are difficult to generalized into medical imaging field challenged by complex medical texture features. To overcome this challenge, we propose a Contour Attention Preserving (CAP) method based on lung cavity edge extraction. The contour prior features are injected to attention layer via a parameter regularization and we optimize the robust empirical risk with hybrid distance metric. We then introduce a new cross-nation CT scan dataset to evaluate the generalization capability of the adversarial robustness under distribution shift. Experimental results indicate that the proposed method achieves state-of-the-art performance in multiple adversarial defense and generalization tasks. The code and dataset are available at https://github.com/Quinn777/CAP.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 30 Nov 2022.
Builds on
49 of 62 references.
References · 49
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2013Intriguing properties of neural networkscited by 5,155
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2016Adversarial examples in the physical worldcited by 1,769
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
37 more
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,013
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
- 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
- 2020Fast is better than free: Revisiting adversarial trainingcited by 727
- 2020Overfitting in adversarially robust deep learningcited by 506
- 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
- 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
- 2021A Fourier-based Framework for Domain Generalizationcited by 290
- 2020COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Imagescited by 264
- 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
- 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
- 2021Vision Transformers are Robust Learnerscited by 207
- 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 172
- 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 153
- 2022Understanding The Robustness in Vision Transformerscited by 144
- 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
- 2019Adversarial Training Can Hurt Generalizationcited by 132
- 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
- 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 111
- 2020MosMedData: Chest CT Scans With COVID-19 Related Findings Datasetcited by 104
- 2017Medical Image Analysis using Convolutional Neural Networks: A Reviewcited by 99
- 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
- 2020Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalizationcited by 73
- 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 71
- 2020COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Imagescited by 60
- 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
- 2018Improving the Generalization of Adversarial Training with Domain Adaptationcited by 48
- 2020Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Freecited by 48
- 2021Consistency Regularization for Adversarial Robustnesscited by 42
- 2019Jacobian Adversarially Regularized Networks for Robustnesscited by 40
- 2021Adaptive Consistency Regularization for Semi-Supervised Transfer Learningcited by 37
- 2017Comparing deep neural networks against humans: object recognition when the signal gets weakercited by 34
- 2020Improving Adversarial Robustness via Unlabeled Out-of-Domain Datacited by 23
- 2022Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentationcited by 11
- 2021Jekyll: Attacking Medical Image Diagnostics using Deep Generative Modelscited by 10
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 2.
3 papers.