A Simple Structure For Building A Robust Model
This work addresses security concerns for deep learning applications, particularly in computer vision, by enhancing model robustness against adversarial attacks, but it appears incremental as it builds on existing adversarial training methods.
The paper tackles improving the robustness of deep learning models against adversarial attacks by proposing a simple architecture that adds an adversarial sample detection network for cooperative training and a new data sampling strategy incorporating multiple attacks. The results, tested on the Cifar10 dataset, show a positive effect on model robustness, though no specific numbers are provided.
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 .