DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
This addresses a safety problem in AI for computer vision applications, but it is incremental as it applies an existing denoising method to a specific domain.
The paper tackles the vulnerability of deep learning models in semantic segmentation to adversarial attacks by proposing a denoising autoencoder to remove perturbations and restore original images, with experimental verification across various noise distributions.
Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an adversarial attack. This is a problem combined with the safety of artificial intelligence, which has recently been studied a lot. These attacks have shown that they can fool models of image classification, semantic segmentation, and object detection. We point out this attack can be protected by denoise autoencoder, which is used for denoising the perturbation and restoring the original images. We experiment with various noise distributions and verify the effect of denoise autoencoder against adversarial attack in semantic segmentation.