Boundary samples are special inputs to artificial neural networks crafted to identify the execution environment used for inference by the resulting output label. The paper presents and evaluates algorithms to generate transparent boundary samples. Transparency refers to a small perceptual distortion of the host signal (i.e., a natural input sample). For two established image classifiers, ResNet on FMNIST and CIFAR10, we show that it is possible to generate sets of boundary samples which can identify any of four tested microarchitectures. These sets can be built to not contain any sample with a worse peak signal-to-noise ratio than 70dB. We analyze the relationship between search complexity and resulting transparency.
翻译:边界样品是对人为神经网络的特殊投入,这些网络旨在确定用于根据所产生的输出标签进行推断的执行环境。本文提出并评价生成透明边界样品的算法。透明是指主机信号的轻微概念扭曲(即自然输入样品)。对于两个既定图像分类器,即FMNIST和CIFAR10,我们表明,可以生成一组边界样品,用以识别四个经过测试的微结构体中的任何一个。这些装置可以建造成不包含任何比70dB更高峰的信号与噪音比率更差的样品。我们分析了搜索复杂性和由此产生的透明度之间的关系。