Xiaodan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiaodan Zhang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Guoyi Li
Chinese Academy of Sciences
2 shared publications - Honglei Lv
Institute of Information Engineering Chinese Academy of Sciences China
2 shared publications - Jingyuan Hu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
2 shared publications - Liya Su
Institute of Information Engineering Chinese Academy of Sciences
2 shared publications - Shang Shang
Institute of Information Engineering Chinese Academy of Sciences
2 shared publications - Wei Zhou
Institute of Information Engineering, Chinese Academy of Sciences
2 shared publications
Latest Publications
- 20 October 2025
- Published by Springer Nature
- p. 100-118
AnsBridge: Towards Secure Cross-Chain Interoperability via Anonymous and Verifiable Validators
- 20 October 2025
- Published by Springer Nature
- p. 100-118
AnsBridge: Towards Secure Cross-Chain Interoperability via Anonymous and Verifiable Validators
- 5 September 2024
- Published by Springer Nature
- p. 146-165
IntentObfuscator: A Jailbreaking Method via Confusing LLM with Prompts
- 5 September 2024
- Published by Springer Nature
- p. 146-165
IntentObfuscator: A Jailbreaking Method via Confusing LLM with Prompts
- 1 August 2024
- Published by Springer Nature
- p. 3-13
LLM-Driven External Knowledge Integration Network for Rumor Detection
- 1 August 2024
- Published by Springer Nature
- p. 3-13
LLM-Driven External Knowledge Integration Network for Rumor Detection
- Open Access
Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent
To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by obfuscating the true intentions behind user prompts.This approach compels LLMs to inadvertently generate restricted content, bypassing their built-in content security measures. We detail two implementations under this framework: "Obscure Intention" and "Create Ambiguity", which manipulate query complexity and ambiguity to evade malicious intent detection effectively. We empirically validate the effectiveness of the IntentObfuscator method across several models, including ChatGPT-3.5, ChatGPT-4, Qwen and Baichuan, achieving an average jailbreak success rate of 69.21\%. Notably, our tests on ChatGPT-3.5, which claims 100 million weekly active users, achieved a remarkable success rate of 83.65\%. We also extend our validation to diverse types of sensitive content like graphic violence, racism, sexism, political sensitivity, cybersecurity threats, and criminal skills, further proving the substantial impact of our findings on enhancing 'Red Team' strategies against LLM content security frameworks.
Open AccessCan LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent
To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by obfuscating the true intentions behind user prompts.This approach compels LLMs to inadvertently generate restricted content, bypassing their built-in content security measures. We detail two implementations under this framework: "Obscure Intention" and "Create Ambiguity", which manipulate query complexity and ambiguity to evade malicious intent detection effectively. We empirically validate the effectiveness of the IntentObfuscator method across several models, including ChatGPT-3.5, ChatGPT-4, Qwen and Baichuan, achieving an average jailbreak success rate of 69.21\%. Notably, our tests on ChatGPT-3.5, which claims 100 million weekly active users, achieved a remarkable success rate of 83.65\%. We also extend our validation to diverse types of sensitive content like graphic violence, racism, sexism, political sensitivity, cybersecurity threats, and criminal skills, further proving the substantial impact of our findings on enhancing 'Red Team' strategies against LLM content security frameworks.
- 17 March 2023
- Published by Springer Nature
- p. 207-223
A Heterogeneous Propagation Graph Model for Rumor Detection Under the Relationship Among Multiple Propagation Subtrees
- 17 March 2023
- Published by Springer Nature
- p. 207-223
A Heterogeneous Propagation Graph Model for Rumor Detection Under the Relationship Among Multiple Propagation Subtrees
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 15722-15738
Adversarial Text Generation by Search and Learning
Guoyi Li, Bingkang Shi, Zongzhen Liu, Dehan Kong, Yulei Wu, Xiaodan Zhang, Longtao Huang, Honglei Lyu. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 15722-15738
Open AccessAdversarial Text Generation by Search and Learning
Guoyi Li, Bingkang Shi, Zongzhen Liu, Dehan Kong, Yulei Wu, Xiaodan Zhang, Longtao Huang, Honglei Lyu. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- Open Access
Pay attention to emoji: Feature Fusion Network with EmoGraph2vec Model for Sentiment Analysis
With the explosive growth of social media, opinionated postings with emojis have increased explosively. Many emojis are used to express emotions, attitudes, and opinions. Emoji representation learning can be helpful to improve the performance of emoji-related natural language processing tasks, especially in text sentiment analysis. However, most studies have only utilized the fixed descriptions provided by the Unicode Consortium without consideration of actual usage scenarios. As for the sentiment analysis task, many researchers ignore the emotional impact of the interaction between text and emojis. It results that the emotional semantics of emojis cannot be fully explored. In this work, we propose a method called EmoGraph2vec to learn emoji representations by constructing a co-occurrence graph network from social data and enriching the semantic information based on an external knowledge base EmojiNet to embed emoji nodes. Based on EmoGraph2vec model, we design a novel neural network to incorporate text and emoji information into sentiment analysis, which uses a hybrid-attention module combined with TextCNN-based classifier to improve performance. Experimental results show that the proposed model can outperform several baselines for sentiment analysis on benchmark datasets. Additionally, we conduct a series of ablation and comparison experiments to investigate the effectiveness and interpretability of our model.
Open AccessPay attention to emoji: Feature Fusion Network with EmoGraph2vec Model for Sentiment Analysis
With the explosive growth of social media, opinionated postings with emojis have increased explosively. Many emojis are used to express emotions, attitudes, and opinions. Emoji representation learning can be helpful to improve the performance of emoji-related natural language processing tasks, especially in text sentiment analysis. However, most studies have only utilized the fixed descriptions provided by the Unicode Consortium without consideration of actual usage scenarios. As for the sentiment analysis task, many researchers ignore the emotional impact of the interaction between text and emojis. It results that the emotional semantics of emojis cannot be fully explored. In this work, we propose a method called EmoGraph2vec to learn emoji representations by constructing a co-occurrence graph network from social data and enriching the semantic information based on an external knowledge base EmojiNet to embed emoji nodes. Based on EmoGraph2vec model, we design a novel neural network to incorporate text and emoji information into sentiment analysis, which uses a hybrid-attention module combined with TextCNN-based classifier to improve performance. Experimental results show that the proposed model can outperform several baselines for sentiment analysis on benchmark datasets. Additionally, we conduct a series of ablation and comparison experiments to investigate the effectiveness and interpretability of our model.
- 2 December 2021
- Published by Springer Nature
- p. 3-11
Emoji-Based Co-Attention Network for Microblog Sentiment Analysis
- 2 December 2021
- Published by Springer Nature
- p. 3-11
Emoji-Based Co-Attention Network for Microblog Sentiment Analysis
- Open Access
DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction
Information diffusion prediction is a fundamental task for understanding the information propagation process. It has wide applications in such as misinformation spreading prediction and malicious account detection. Previous works either concentrate on utilizing the context of a single diffusion sequence or using the social network among users for information diffusion prediction. However, the diffusion paths of different messages naturally constitute a dynamic diffusion graph. For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance. For another, they cannot learn users' dynamic preferences. Intuitively, users' preferences are changing as time goes on and users' personal preference determines whether the user will repost the information. Thus, it is beneficial to consider users' dynamic preferences in information diffusion prediction. In this paper, we propose a novel dynamic heterogeneous graph convolutional network (DyHGCN) to jointly learn the structural characteristics of the social graph and dynamic diffusion graph. Then, we encode the temporal information into the heterogeneous graph to learn the users' dynamic preferences. Finally, we apply multi-head attention to capture the context-dependency of the current diffusion path to facilitate the information diffusion prediction task. Experimental results show that DyHGCN significantly outperforms the state-of-the-art models on three public datasets, which shows the effectiveness of the proposed model.
Open AccessDyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction
Information diffusion prediction is a fundamental task for understanding the information propagation process. It has wide applications in such as misinformation spreading prediction and malicious account detection. Previous works either concentrate on utilizing the context of a single diffusion sequence or using the social network among users for information diffusion prediction. However, the diffusion paths of different messages naturally constitute a dynamic diffusion graph. For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance. For another, they cannot learn users' dynamic preferences. Intuitively, users' preferences are changing as time goes on and users' personal preference determines whether the user will repost the information. Thus, it is beneficial to consider users' dynamic preferences in information diffusion prediction. In this paper, we propose a novel dynamic heterogeneous graph convolutional network (DyHGCN) to jointly learn the structural characteristics of the social graph and dynamic diffusion graph. Then, we encode the temporal information into the heterogeneous graph to learn the users' dynamic preferences. Finally, we apply multi-head attention to capture the context-dependency of the current diffusion path to facilitate the information diffusion prediction task. Experimental results show that DyHGCN significantly outperforms the state-of-the-art models on three public datasets, which shows the effectiveness of the proposed model.