mlsanityData to 7 Oct 2026

A Simple Structure For Building A Robust Model

arXiv 2204.11596 ↗First posted 25 Apr 2022cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep learning models is to perform adversarial training, which allows the model to be compatible with samples that are deliberately created for use in attacking the model.Based on this, we propose a simple architecture to build a model with a certain degree of robustness, which improves the robustness of the trained network by adding an adversarial sample detection network for cooperative training. At the same time, we design a new data sampling strategy that incorporates multiple existing attacks, allowing the model to adapt to many different adversarial attacks with a single training.We conducted some experiments to test the effectiveness of this design based on Cifar10 dataset, and the results indicate that it has some degree of positive effect on the robustness of the model.Our code could be found at https://github.com/dowdyboy/simple_structure_for_robust_model .

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 37 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

33 of 37 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2017Detecting Adversarial Samples from Artifactscited by 244
  10. 2016A guide to convolution arithmetic for deep learningcited by 182
  11. 2017Demystifying Neural Style Transfercited by 152
  12. 2019A Survey of Deep Learning-based Object Detectioncited by 106
21 more
  1. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 101
  2. 2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
  3. 2019The Limitations of Adversarial Training and the Blind-Spot Attackcited by 63
  4. 2018Adversarially Robust Optimization with Gaussian Processescited by 61
  5. 2021A Survey On Universal Adversarial Attackcited by 59
  6. 2020Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspectivecited by 58
  7. 2020A survey on Semi-, Self- and Unsupervised Learning for Image Classificationcited by 55
  8. 2020Auxiliary Tasks Speed Up Learning PointGoal Navigationcited by 52
  9. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  10. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  11. 2020Federated Model Distillation with Noise-Free Differential Privacycited by 40
  12. 2016Deep Model Compression: Distilling Knowledge from Noisy Teacherscited by 35
  13. 2021A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Modelscited by 24
  14. 2021Achieving Model Robustness through Discrete Adversarial Trainingcited by 23
  15. 2021Neural tensor contractions and the expressive power of deep neural quantum statescited by 21
  16. 2015Deep Learning Algorithms with Applications to Video Analytics for A Smart City: A Surveycited by 6
  17. 2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
  18. 2022When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentationcited by 5
  19. 2016Deep Learning and Its Applications to Machine Health Monitoring: A Surveycited by 4
  20. 2020A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samplescited by 4
  21. 2022Dissecting the impact of different loss functions with gradient surgerycited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Quantifying probabilistic robustness of tree-based classifiers against natural distortionscited by 0