Hiding Function with Neural Networks
Yusheng Guo, Zhenxing Qian, Xinpeng Zhang · 2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP) · 2022
In this paper, we show that neural networks can hide a specific task while finishing a common one. We leverage the excellent fitting ability of neural networks to train two tasks simultaneously. In a classification example, the first task is normally trained by the traditional crossentropy loss. The output of the second task can be obtained by the product of the penultimate layer and a predefined random matrix. A well-trained network looks like a benign classifier and will not arouse suspicion. For certain people, they can use a predefined random matrix to turn on the second covert function of the neural network. Experimental results demonstrate that the hidden tasks can achieve satisfactory performance without affecting the original tasks.