Qi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qi Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Yunchun Zhang
Yunnan University
2 shared publications - Cencen Liu
University of Electronic Science and Technology of China
1 shared publication - Chuanjie Liu
Sichuan University
1 shared publication - Dezhang Zheng
University of Electronic Science and Technology of China
1 shared publication Feiyang Huang
1 shared publicationHao Liu
1 shared publication
Latest Publications
- 25 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 173
Attention-based backdoor attacks against natural language processing models
- 25 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 173
Attention-based backdoor attacks against natural language processing models
- 12 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (16) , 26837-26851
Deep Hashing for Malware Family Classification and New Malware Identification
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%.
- 12 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (16) , 26837-26851
Deep Hashing for Malware Family Classification and New Malware Identification
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%.
- 22 September 2023
- Published by Springer Nature
- p. 505-517
Prompt-Oriented Fine-Tuning Dual Bert for Aspect-Based Sentiment Analysis
- 22 September 2023
- Published by Springer Nature
- p. 505-517
Prompt-Oriented Fine-Tuning Dual Bert for Aspect-Based Sentiment Analysis