Abstract:

The traditional way of hardware trojan detection based on electrical signal detection has problems of low positive rate, low efficiency and high cost. To solve these problems, we propose a new way of hardware trojan detection based on deep learning which is not electrical signal detection. First, the algorithm changes chip microscopic images of low resolution into chip microscopic images of high resolution by using an enhanced residual network. Then these chip microscopic images of high resolution will generate another chip microscopic images which are similar to those of the golden model. The algorithm for image enhancement distinguishes between target area and background area by combining with the algorithm of image segmentation. Finally, we use the change detection algorithm to detect the hardware trojans existing in the chip after removing minor interference due to industrial noise. Through the experiments on the micrograph dataset of the chip, the positive detection rate of the hardware trojan detection method based on deep learning is as high as 92.4%. Compared with the traditional electrical signal detection method, our algorithm has the advantages of higher precision, faster speed, and easier operation.

Key words: hardware trojan detection, deep learning, image enhancement, image segmentation, mathematical morphology, change detection