论文标题
休眠的神经木马
Dormant Neural Trojans
论文作者
论文摘要
我们提出了一种用于神经网络后门攻击的新方法。与现有的训练时间攻击不同，在训练后，木马网络将对特洛伊木马的触发作出响应，我们的方法插入了一个特洛伊木马，该特洛伊木马会一直处于休眠状态，直到被激活为止。通过对网络的权重参数的特定扰动仅是攻击者已知的。我们的分析和实验结果表明，休眠的木马网络可以通过最新的后门检测方法有效地逃避检测。
We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant until it is activated. The activation is realized through a specific perturbation to the network's weight parameters only known to the attacker. Our analysis and the experimental results demonstrate that dormant Trojaned networks can effectively evade detection by state-of-the-art backdoor detection methods.
