Convolutional neural networks have gained vast popularity due to their excellent performance in the fields of computer vision, image processing, and others. Unfortunately, it is now well known that convolutional networks often produce erroneous results - for example, minor perturbations of the inputs of these networks can result in severe classification errors. Numerous verification approaches have been proposed in recent years to prove the absence of such errors, but these are typically geared for fully connected networks and suffer from exacerbated scalability issues when applied to convolutional networks. To address this gap, we present here the Cnn-Abs framework, which is particularly aimed at the verification of convolutional networks. The core of Cnn-Abs is an abstraction-refinement technique, which simplifies the verification problem through the removal of convolutional connections in a way that soundly creates an over-approximation of the original problem; and which restores these connections if the resulting problem becomes too abstract. Cnn-Abs is designed to use existing verification engines as a backend, and our evaluation demonstrates that it can significantly boost the performance of a state-of-the-art DNN verification engine, reducing runtime by 15.7% on average.
翻译:由于在计算机视觉、图像处理和其他领域的出色表现,革命神经网络已获得广泛欢迎。不幸的是,现在众所周知,革命网络往往产生错误的结果,例如,这些网络投入的轻微扰动可能导致严重的分类错误。近年来提出了许多核查方法,以证明不存在这种错误,但这些方法通常都针对完全连接的网络,并且在应用到革命网络时会遇到更严重的可缩缩化问题。为了弥补这一差距,我们在这里提出Cnn-Abs框架,特别旨在核查革命网络。Cnn-Abs的核心是一种抽象的精炼技术,它通过消除革命关系来简化核查问题,从而造成对最初问题的正确过度认同;如果由此造成的问题变得过于抽象,则恢复这些联系。Cnn-Abs的设计是利用现有的核查引擎作为后端,我们的评估表明,它能够大大地提高国家平均7.7%的引擎运行率。