
The author introduces the concept of training a TrojanNet within a carrier network for distinct tasks, emphasizing shared parameters but no feature sharing. The approach involves optimizing task losses for public and secret datasets simultaneously.


coremsg

Modern neural networks often contain significantly more parameters than the size of their training data. We show that this excess capacity provides an opportunity for embedding secret machine learning models within a t…

On Hiding Neural Networks Inside Neural Networks

Unveiling-the-TrojanNet-Concept-in-Neural-Networks


Unveiling the TrojanNet Concept in Neural Networks
