论文标题
SINVAD：基于搜索的DNN图像分类器测试输入生成的图像空间导航
SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation
论文作者
论文摘要
深度神经网络（DNN）的测试变得越来越重要，因为DNN被安全关键系统广泛采用。尽管已经提出了许多测试充足性标准，但许多类型的DNN的自动测试输入生成仍然是一个挑战，因为原始输入空间太大，无法随机采样或导航和搜索可见的输入。因此，基于变质测试原理，当前的DNN测试技术取决于对现有输入的小局部扰动。我们提出了新的方法来搜索整个图像空间，而是在类似于真正的训练分布的合理输入空间上。该空间是使用变量自动编码器（VAE）构建的，并在其潜在矢量空间中导航。我们表明，该空间有助于产生测试输入，这些输入可以揭示有关DNN在处理现实测试时鲁棒性的信息，从而通过高度结构化的图像的空间开放了有意义的探索。
The testing of Deep Neural Networks (DNNs) has become increasingly important as DNNs are widely adopted by safety critical systems. While many test adequacy criteria have been suggested, automated test input generation for many types of DNNs remains a challenge because the raw input space is too large to randomly sample or to navigate and search for plausible inputs. Consequently, current testing techniques for DNNs depend on small local perturbations to existing inputs, based on the metamorphic testing principle. We propose new ways to search not over the entire image space, but rather over a plausible input space that resembles the true training distribution. This space is constructed using Variational Autoencoders (VAEs), and navigated through their latent vector space. We show that this space helps efficiently produce test inputs that can reveal information about the robustness of DNNs when dealing with realistic tests, opening the field to meaningful exploration through the space of highly structured images.
