论文标题
通过图像质量评估进行稳健分类
Towards Robust Classification with Image Quality Assessment
论文作者
论文摘要
最近的研究表明，深层卷积神经网络（DCNN）容易受到对抗例子的影响，对感知质量以及图像的获取条件敏感。这些发现引起了对基于DCNN的关键任务应用程序的重要关注。在文献中，已经引入了各种防御策略，以提高DCNN的鲁棒性，包括重新训练整个模型，并注入良性噪声，对抗性示例或添加额外的层。在本文中，我们研究了对抗操作与图像质量之间的联系，随后提出了一种保护机制，该机制不需要重新训练DCNN。我们的方法将图像质量评估与知识蒸馏结合在一起，以检测会触发DCCN的输入图像，从而产生明显的错误结果。以在Imagenet上训练的Resnet模型为例，我们证明了检测器可以有效地识别质量和对抗性图像差。
Recent studies have shown that deep convolutional neural networks (DCNN) are vulnerable to adversarial examples and sensitive to perceptual quality as well as the acquisition condition of images. These findings raise a big concern for the adoption of DCNN-based applications for critical tasks. In the literature, various defense strategies have been introduced to increase the robustness of DCNN, including re-training an entire model with benign noise injection, adversarial examples, or adding extra layers. In this paper, we investigate the connection between adversarial manipulation and image quality, subsequently propose a protective mechanism that doesnt require re-training a DCNN. Our method combines image quality assessment with knowledge distillation to detect input images that would trigger a DCCN to produce egregiously wrong results. Using the ResNet model trained on ImageNet as an example, we demonstrate that the detector can effectively identify poor quality and adversarial images.
