Tingyuan Nie’s research while affiliated with Qingdao University of Technology and other places

The globalization of the Integrated Circuit (IC) supply chain has introduced the risk of Hardware Trojan (HT) insertion. We propose an unsupervised Hardware Trojan detection method based on the Enhanced Local Outlier Factor (ELOF) algorithm to detect HT efficiently. This method extracts structural and testability features and employs the scoring mechanism of the ELOF algorithm to emphasize the deviation of suspicious HT nets from clusters. Experimental results on Hardware Trojan libraries show that the method achieves an average prediction accuracy (A) of 97.36%, a True Negative Rate (TNR) of 97.81%, a precision (P) of 40.94%, and an F-measure of 49.28%, all of which outperform the Local Outlier Factor (LOF) algorithm and Cluster-Based Local Outlier Factor (CBLOF) algorithm. Notably, the method exhibits superior performance in terms of True Positive Rate (TPR), reaching 70.86%, indicating its efficiency in identifying HT and reducing false negatives. The results demonstrate that the proposed algorithm and feature combination in the approach can significantly enhance the efficiency of Trojan detection.

In the task of multi-label aerial image classification, various objects and land cover in an image are usually represented by multiple labels which are treated equally. However, from a semantic point of view, the importance of multiple labels are different in a specific scene. There is often a prime label in the image that plays a "leading" role. Obtaining the most important label from candidate multiple labels is crucial, because it best represents the semantics of the entire image. In this letter, we attempt to automatically obtain the prime label of each image from several existing multi-label aerial image datasets without additional supervision cost. In other words, the prime labels are only used to evaluate the performance of models during testing and do not participate in the training process. Therefore, it is essentially a weakly supervised learning task. For this novel aerial image classification task, corresponding datasets are provided in this letter firstly, including over head images with multi-labels for training and prime labels for testing. Then the baselines on the above datasets are provided. Finally, a new prime label learning method is proposed, which improves the baseline accuracy by about 14% and reaches the state-of-the-art on current datasets.

Identifying the feature of the circuit network is a crucial step to understanding the behavior of the Very Large Scale Integration (VLSI). Unfortunately, the growing complexity of the VLSI design makes enormous computations for estimating the property of the network. We propose a machine learning framework to overcome the intractable estimation of feature importance in the circuit network. We extract complex network features at the placement stage and compute circuit wire length at the routing stage, then study their correlation using machine learning and estimate the importance of complex network features by the learned correlation. The experimental result on TAU 2017 Benchmark shows the high efficiency of the framework that the prediction accuracy achieves an average of 96.722%. The estimated importance of complex network features is in order of the number of nodes, the average degree, the average edge weight, the average betweenness, the average strength, and the average weighted clustering coefficient. The result is convincing and consistent with the previous work, demonstrating the reliability of our method.

Efficient three-dimensional (3D) object recognition plays an important role in the 3D reconstruction of light-field displays. However, presently, the error rate of 3D implicit shape object recognition remains high, because the local features are sparse in the geometric expression of 3D reconstruction. To address this issue, a hypothesis verification method based on semi-supervised active learning-based K-means++ combined with 3D feature extraction is proposed. The proposed approach consists of the offline and online phases. The algorithm time complexity is O(n) and O(n2), respectively. The offline phase includes keypoint detection, normal estimation, fast point feature histograms (FPFH) descriptor extraction, geometric word weight saving, and indexing structure construction. In addition to the FPFH extraction, the online phase includes nearest geometric word searching, corresponding direction and center voting, and non-maximum suppression. Comparative experiments were conducted in which the models and scenes were tested on the 3D datasets Mian and Tosca that is high-resolution. The experimental results demonstrate that the proposed method resolves the low recognition rate problem of 3D implicit objects, with the highest 3D intersection over union (IoU) reaching 88.89%.

Street view image (SVI) is becoming one of the most essential proximity sensing data for urban land-use study. Because of the highly abstract nature of their labels (e.g., commercial area), straight usage of end-to-end visual models often perform poorly. Recently proposed ‘bottom-up and top-down’ framework has achieved remarkable performance, which transforms visual classification task into text sequence classification task. However, in the ‘top-down’ phase, the long-distance dependence of text information still exists. On the other hand, in the ‘bottom-up’ phase, better detectors are also needed to further extract visual features. In this letter, the idea of ‘feature adaptive weighting’ (FAW), which was derived from the attention mechanism, is used in both phases to improve the overall performance. ‘Self-correlation guided feature adaptive weighting’ (S-FAW) is introduced in the first phase to improve building detection. In the second phase, ‘cross-correlation guided feature adaptive weighting’ (C-FAW) is used to enhance the connections between detected individual buildings. Experimental results show that the proposed FAWNet can effectively improve the performance of the two-phase framework in both phases and surpass the mainstream end-to-end models.

The research on artificial networks is of great significance for understanding and improving the functionality of the artificial system. In this paper, we study the complexity and robustness of the weighted circuit network of the placement. The result on circuit benchmarks shows that the network behaves as a small-world property of the broad-scale class, and the large-scale circuit tends to be with a strong small-world property. The correlation between network efficiency and circuit scale presents a power-law distribution. The networks represent diverse robustness to different attack strategies due to their inherent characteristics. Especially IS (Initial Strength) attack strategy outperforms ID (Initial Degree) attack strategy for large-scale networks.