SYSTEM AND METHOD FDR DETECTING BACKDOOR ATTACKS IN CONVOLUTIONAL NEURAL NETWORKS

Described is a system for detecting backdoor attacks in deep convolutional neural networks (CNNs). The system compiles specifications of a pretrained CNN into an executable model, resulting in a compiled model. A set of Universal Litmus Patterns (ULPs) are fed through the compiled model, resulting in a set of model outputs. The set of model outputs are classified and used to determine presence of a backdoor attack in the pretrained CNN. The system performs a response based on the presence of the backdoor attack. 描述了一种对深度卷积神经网络(CNN)中的后门攻击进行检测的系统。所述系统将经预训练的CNN的规范编译为可执行模型，从而产生编译模型。将通用石蕊模式(ULP)集馈送通过编译模型，从而产生模型输出集。对模型输出集进行分类，并且使用模型输出集来确定经预训练的CNN中的后门攻击的存在。所述系统基于后门攻击的存在来执行响应。