ZLZikun Liao

Zikun Liao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zikun Liao has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Deep Hashing for Malware Family Classification and New Malware Identification

    by Yunchun Zhang, Zikun Liao, Ning Zhang, Shaohui Min, Qi Wang, Tony Q. S. Quek, Mingxiong Zhao

    Although numerous state-of-the-art deep neural networks have recently been proposed for malware classification, effectively detecting malware on a large-scale sample set and identifying zero-day or new malware variants still pose significant challenges. To address this issue, a deep hashing-based malware classification model is designed for malware identification, including two parts: 1) ResNet50-based deep hashing for malware retrieval and 2) voting-based malware classification. Specifically, multiple deep hashing models are developed by extracting the high-layer outputs (feature maps) from the ResNet50 trained with malware gray-scale images in the first part. In this case, to maximize the Hamming distance or dissimilarity among hash values computed with malware samples under different families, a ResNet50-based deep polarized network (RNDPN) is designed to return $Top\;K$ similar samples. In the second part, we propose a majority-voting and a Hamming-distance-based voting for malware identification according to the retrieved results. The experiment results show that RNDPN outperforms the other six deep hashing models with 97.54% mean average precision (mAP) for malware retrieval when only 40 similar examples are retrieved, where the best results for all deep hashing models are observed with 48-bits hashing code length. Furthermore, the Hamming distance-based voting method implemented with RNDPN demonstrates unparalleled performance in malware classification compared to other models. Notably, it achieves exceptional results in two key aspects: 1) malware classification accuracy with an impressive accuracy rate of 96.5% and 2) the identification of new or zero-day malware with a commendable accuracy of 85.7%.


  • Deep Neural Network-based Chinese Natural Language Generation on Dynamic Auxiliary Words

    by Rui Xiao, Qi Shen, Zixuan Li, Xueqing Ge, Yunchun Zhang, Zikun Liao

    Many tasks have been solved by deep neural networks in the field of natural language processing (NLP) and natural language generation (NLG). However, some critical issues in teaching Chinese as a foreign or second language for foreign students are still unsolved. The teaching and learning of dynamic auxiliary words (le, zhe and guo) in Chinese are seldom considered in deep learning-powered applications. Taking three typical dynamic auxiliary words in Chinese as inputs, three Chinese language generation models are designed and evaluated in our work. The designed models, including BERT, BERT-WWM and RoBERTa, are optimized by observing the characteristics of two typical Chinese corpora. The experimental results show that BERT-WWM achieves better accuracy than RoBERTa and BERT by 29.4% and 3.983% on average, respectively. We also summarized the major error patterns on dynamic auxiliary word zhe based on detailed observations on falsely generated samples.