Detecting and Segmenting Adversarial Graphics Patterns from Images
arXiv:2108.09383
Abstract
Adversarial attacks pose a substantial threat to computer vision system security, but the social media industry constantly faces another form of "adversarial attack" in which the hackers attempt to upload inappropriate images and fool the automated screening systems by adding artificial graphics patterns. In this paper, we formulate the defense against such attacks as an artificial graphics pattern segmentation problem. We evaluate the efficacy of several segmentation algorithms and, based on observation of their performance, propose a new method tailored to this specific problem. Extensive experiments show that the proposed method outperforms the baselines and has a promising generalization capability, which is the most crucial aspect in segmenting artificial graphics patterns.
arXiv commentICCV 2021 Workshop on Adversarial Robustness in the Real World
References in corpus (6)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Deeply supervised salient object detection with short connections
- Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
- DropBlock: A regularization method for convolutional networks
- Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)