Searcharxiv⌕ Search

arXiv subjects

Yuntao Liu

Publications and source records attributed to Yuntao Liu.

21 records · Page 2Linked to original sources

Visual Tree Convolutional Neural Network in Image Classification

In image classification, Convolutional Neural Network(CNN) models have achieved high performance with the rapid development in deep learning. However, some categories in the image datasets are more difficult to distinguished than others. Improving the classification accuracy on these confused categories is benefit to the overall performance. In this paper, we build a Confusion Visual Tree(CVT) based on the confused semantic level information to identify the confused categories. With the information provided by the CVT, we can lead the CNN training procedure to pay more attention on these confused categories. Therefore, we propose Visual Tree Convolutional Neural Networks(VT-CNN) based on the original deep CNN embedded with our CVT. We evaluate our VT-CNN model on the benchmark datasets CIFAR-10 and CIFAR-100. In our experiments, we build up 3 different VT-CNN models and they obtain improvement over their based CNN models by 1.36%, 0.89% and 0.64%, respectively.

cs.CV↗

Neural Trojans

While neural networks demonstrate stronger capabilities in pattern recognition nowadays, they are also becoming larger and deeper. As a result, the effort needed to train a network also increases dramatically. In many cases, it is more practical to use a neural network intellectual property (IP) that an IP vendor has already trained. As we do not know about the training process, there can be security threats in the neural IP: the IP vendor (attacker) may embed hidden malicious functionality, i.e. neural Trojans, into the neural IP. We show that this is an effective attack and provide three mitigation techniques: input anomaly detection, re-training, and input preprocessing. All the techniques are proven effective. The input anomaly detection approach is able to detect 99.8% of Trojan triggers although with 12.2% false positive. The re-training approach is able to prevent 94.1% of Trojan triggers from triggering the Trojan although it requires that the neural IP be reconfigurable. In the input preprocessing approach, 90.2% of Trojan triggers are rendered ineffective and no assumption about the neural IP is needed.

cs.CR↗

Crystal growth and phase diagram of 112-type iron pnictide superconductor Ca1-yLayFe1-xNixAs2

We report a systematic crystal growth and characterization of Ca$_{1-y}$La$_{y}$Fe$_{1-x}$Ni$_{x}$As$_{2}$, the newly discovered 112-type iron-based superconductor. After substituting Fe by a small amount of Ni, bulk superconductivity is successfully obtained in high quality single crystals sized up to 6 mm. Resistivity measurements indicate common features for transport properties in this 112-type iron pnictide, suggest strong scattering from chemical dopants. Together with the superconducting transition temperature $T_c$, and the Neel temperature $T_N$ determined by the elastic neutron scattering, we sketch a three-dimensional phase diagram in the combination of both Ni and La dopings.

cond-mat.supr-con↗