摘要
攻击者可以通过侧信道信息(Side-channel)完成模型窃取攻击[17].
[17] Hua W Z, Zhang Z R, Suh G E. Reverse Engineering Convolutional Neural Networks through Side-channel Information Leaks[C]. 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC), 2018: 1-6.
参考链接
Reverse Engineering Convolutional Neural Networks Through Side-channel Information Leaks