Zejun Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zejun Yan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Feifei Zou
Nanfang College, School of Computer Science and Technology, Guangzhou, Guangdong, China
1 shared publication - Qijun Zhang
School of Information Technology, Guangdong University of Finance and Economics, China
1 shared publication - Sijun Chan
School of Information Science, Guangdong University of Finance and Economics, China
1 shared publication - Su Hu
School of Big Data and Artificial Intelligence, Guangdong University of Finance & Economics, Guangzhou, Guangdong, China
1 shared publication - Wei Yu
School of Information Science, Guangdong University of Finance and Economics, China
1 shared publication - Weifa Zheng
School of Information Technology, Guangdong University of Finance and Economics, China
1 shared publication
Latest Publications
- Open Access
- 1 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 341-345
Research on Financial Fraud Text Classification Based on PET-BiLSTM
To address challenges associated with obscure features, unbalanced data, and diverse fraud types in Internet financial texts, this paper proposes the PET-BiLSTM financial fraud text classification model to enhance the semantic understanding and reasoning of financial fraud texts. Crawling news, comments and short messages about financial fraud from open source websites, desensitizing and cleaning the texts, labeling them automatically through LDA topic distribution model and financial fraud thesaurus, constructing prompt templates containing mask positions, forming cloze sentences for each sample, and transforming them into multi-classification tasks. The pre-trained BERT model is used to learn semantic information, combined with bidirectional LSTM (BiLSTM) to extract fraudulent text features, and supervised training is carried out. Experimental results show PET-BiLSTM achieving 89.11% and 84.54% F1 values in multi-classifying fraud types and three-classifying fraud degree identification tasks, surpassing deep learning baselines by 4.21% to 15.35% and 2.21% to 9.12%, respectively. PET-BiLSTM also outperforms ChatGPT in zero-shot prompt learning by 67.11% and 48.54%. The model demonstrates superior performance in understanding knowledge facts and fraud reasoning in the financial fraud text classification task, effectively addressing complex text fraud detection challenges within the financial field.
- 1 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 341-345
Open AccessResearch on Financial Fraud Text Classification Based on PET-BiLSTM
To address challenges associated with obscure features, unbalanced data, and diverse fraud types in Internet financial texts, this paper proposes the PET-BiLSTM financial fraud text classification model to enhance the semantic understanding and reasoning of financial fraud texts. Crawling news, comments and short messages about financial fraud from open source websites, desensitizing and cleaning the texts, labeling them automatically through LDA topic distribution model and financial fraud thesaurus, constructing prompt templates containing mask positions, forming cloze sentences for each sample, and transforming them into multi-classification tasks. The pre-trained BERT model is used to learn semantic information, combined with bidirectional LSTM (BiLSTM) to extract fraudulent text features, and supervised training is carried out. Experimental results show PET-BiLSTM achieving 89.11% and 84.54% F1 values in multi-classifying fraud types and three-classifying fraud degree identification tasks, surpassing deep learning baselines by 4.21% to 15.35% and 2.21% to 9.12%, respectively. PET-BiLSTM also outperforms ChatGPT in zero-shot prompt learning by 67.11% and 48.54%. The model demonstrates superior performance in understanding knowledge facts and fraud reasoning in the financial fraud text classification task, effectively addressing complex text fraud detection challenges within the financial field.
- Open Access
- 22 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 448-451
Research on FIDO Authentication Based on IPv6
The FIDO (Fast Identity Online) protocol is an open standard based on public-key cryptography and designed to provide strong authentication protection. However, most of the current studies are conducted in IPv4 network environments, and there are still relatively few studies on the use of FIDO protocols in IPv6 network environments. With the popularization of IPv6 networks, it is particularly important to study the use of FIDO protocol for identity authentication in IPv6 network environments. The purpose of this paper is to explore the feasibility and security of using FIDO protocol for identity authentication in IPv6 network environment, how to implement FIDO protocol in IPv6 network environment, and conduct an in-depth analysis of its security. Through this study, it is hoped that it can provide a new solution for identity authentication in IPv6 network environment and provide a valuable reference for security research and practice.
- 22 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 448-451
Open AccessResearch on FIDO Authentication Based on IPv6
The FIDO (Fast Identity Online) protocol is an open standard based on public-key cryptography and designed to provide strong authentication protection. However, most of the current studies are conducted in IPv4 network environments, and there are still relatively few studies on the use of FIDO protocols in IPv6 network environments. With the popularization of IPv6 networks, it is particularly important to study the use of FIDO protocol for identity authentication in IPv6 network environments. The purpose of this paper is to explore the feasibility and security of using FIDO protocol for identity authentication in IPv6 network environment, how to implement FIDO protocol in IPv6 network environment, and conduct an in-depth analysis of its security. Through this study, it is hoped that it can provide a new solution for identity authentication in IPv6 network environment and provide a valuable reference for security research and practice.