A Deep Learning Method Based on the Attention Mechanism for Hardware Trojan Detection

Abstract

The chip manufacturing of integrated circuits requires the participation of multiple parties, which greatly increases the possibility of hardware Trojan insertion and poses a significant threat to the entire hardware device landing; however, traditional hardware Trojan detection methods require gold chips, so the detection cost is relatively high. The attention mechanism can extract data with more adequate features, which can enhance the expressiveness of the network. This paper combines an attention module with a multilayer perceptron and convolutional neural network for hardware Trojan detection based on side-channel information, and evaluates the detection results by implementing specific experiments. The results show that the proposed method significantly outperforms machine learning classification methods and network-related methods, such as SVM and KNN, in terms of accuracy, precision, recall, and F1 value. In addition, the proposed method is effective in detecting data containing one or multiple hardware Trojans, and shows high sensitivity to the size of datasets.

Overview of Judicial Text Summarization Method

“…The architecture of the extractive summarization model consists of sentence embedding and document-level encoders. The BERT model is used to create sentence-level encoding vectors, and the document-level encoder employs a multi-layer Transformer structure [38]. Finally, a fully connected layer is applied to the sentence-level encodings to predict the label category for each sentence.…”

“…Micro-average evaluation metrics were added to the BiLSTM-CRFs model to assess the overall performance. Micro-average refers to the arithmetic average of the test results of all samples [38].…”