Exploratory Research on Defense against Natural Adversarial Examples in Image Classification
Source abstract
Abstract
The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natural advers... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (18)
Show source-provided references
1. ImageNet classfication with deep convolutional neural networks
2. Very deep convolutional networks for large-scale image recognition
3. Going deeper with convolutions
4. Deep residual learning for image recognition
5. Convolutional networks with dense connectivity10.1109/TPAMI.2019.2918284 ↗
6. A ConvNet for the 2020s
7. PFCFuse: A poolformer and CNN fusion network for infrared-visible image fusion
8. Decision fusion of CNN and SRC with application to SAR target recognition
9. Intriguing properties of neural networks
10. M. Lee and Z. Kolter, “On physical adversarial patches for object detection,” Statistics, 2019. doi: 10.48550/arXiv.1906.11897.
11. Adversarial camouflage: Hiding physical-world attacks with natural styles
12. Natural adversarial examples
13. Learning deep features for discriminative localization
14. Grad-CAM: Visual explanations from deep networks via gradient-based localization
15. Noise or signal: The role of image backgrounds in object recognition
16. Revisiting unreasonable effectiveness of data in deep learning era
17. Deep frequency principle towards understanding why deeper learning is faster
18. Is robustness the cost of accuracy?— A comprehensive study on the robustness of 18 deep image classification models