Fulan Qian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fulan Qian has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
- Shu Zhao
Anhui University
20 shared publications - Hai Chen
Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China
12 shared publications - Yanping Zhang
Anhui University
10 shared publications Hai Chen
Tsinghua University
7 shared publications- Jie Chen
Anhui University
6 shared publications Shu Zhao
6 shared publications
Latest Publications
- Open Access
- 13 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-31
Focus on Evidence: Relational Structure Enhances LLM Effectiveness in TableQA
Table Question Answering (TableQA) requires reasoning over natural language questions and structured tables and remains challenging due to noisy evidence and complex multi-step reasoning. Recent Large Language Model (LLM)-based approaches typically adopt decomposition–reasoning–validation pipelines that combine Chain-of-Thought (CoT) decomposition, Direct Prompting (DP), Python Agent (PyAgent) execution, and self-validation. However, these methods still largely rely on unconstrained LLM reasoning during decomposition, which may introduce unsupported sub-questions and irrelevant evidence expansion. We propose EV idence- A ware (EVA), a framework that explicitly grounds decomposition on question-relevant table evidence before reasoning begins. EVA first extracts evidence-aware relational structures that associate question semantics with supporting table attributes, thereby constraining sub-question generation within a grounded evidence space. EVA further introduces relation-guided validation and integrates both DP and PyAgent reasoning to improve robustness across different reasoning patterns. Experiments on datasets across multiple LLMs demonstrate that EVA consistently improves reasoning reliability and achieves strong performance across diverse TableQA settings.
- 13 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-31
Open AccessFocus on Evidence: Relational Structure Enhances LLM Effectiveness in TableQA
Table Question Answering (TableQA) requires reasoning over natural language questions and structured tables and remains challenging due to noisy evidence and complex multi-step reasoning. Recent Large Language Model (LLM)-based approaches typically adopt decomposition–reasoning–validation pipelines that combine Chain-of-Thought (CoT) decomposition, Direct Prompting (DP), Python Agent (PyAgent) execution, and self-validation. However, these methods still largely rely on unconstrained LLM reasoning during decomposition, which may introduce unsupported sub-questions and irrelevant evidence expansion. We propose EV idence- A ware (EVA), a framework that explicitly grounds decomposition on question-relevant table evidence before reasoning begins. EVA first extracts evidence-aware relational structures that associate question semantics with supporting table attributes, thereby constraining sub-question generation within a grounded evidence space. EVA further introduces relation-guided validation and integrates both DP and PyAgent reasoning to improve robustness across different reasoning patterns. Experiments on datasets across multiple LLMs demonstrate that EVA consistently improves reasoning reliability and achieves strong performance across diverse TableQA settings.
- 15 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Periodic dynamic adaptive fine-tuning for adversarially robust recommender systems
- 15 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Periodic dynamic adaptive fine-tuning for adversarially robust recommender systems
- 2 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-14
C-FA: Enhancing Transferability through Contrastive Learning and Feature Attention in Point Cloud Attacks
3D classification networks are vulnerable to adversarial examples, which can cross decision boundaries and cause the model to misclassify. However, the adversarial examples generated by the current method do not transferred well across the decision boundaries of various models, resulting in a lower success rate of transfer to a black-box model and poor attack performance against the target model. In this paper, we propose a new method, called C-FA, which revisits the problem of crossing model decision boundaries, generating adversarial examples with improved transferability. We use a contrastive learning strategy, by increasing the difference between the adversarial examples and the benign examples in the feature space, prompting the adversarial examples to cross the decision boundary, leading to misclassification by the model. In addition, considering that perturbing the salient features focused on by the model can effectively enhance the transferability of the generated adversarial examples, we introduce a feature attention mechanism that identifies and weights features that have a more significant impact on decision-making by analyzing the feature gradient. The effectiveness of C-FA and its competitiveness against existing state-of the-art techniques are confirmed through extensive experiments on six representative networks including PointNet, PointNet++, DGCNN, PointConv, PCT, and Mamba3D.
- 2 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-14
C-FA: Enhancing Transferability through Contrastive Learning and Feature Attention in Point Cloud Attacks
3D classification networks are vulnerable to adversarial examples, which can cross decision boundaries and cause the model to misclassify. However, the adversarial examples generated by the current method do not transferred well across the decision boundaries of various models, resulting in a lower success rate of transfer to a black-box model and poor attack performance against the target model. In this paper, we propose a new method, called C-FA, which revisits the problem of crossing model decision boundaries, generating adversarial examples with improved transferability. We use a contrastive learning strategy, by increasing the difference between the adversarial examples and the benign examples in the feature space, prompting the adversarial examples to cross the decision boundary, leading to misclassification by the model. In addition, considering that perturbing the salient features focused on by the model can effectively enhance the transferability of the generated adversarial examples, we introduce a feature attention mechanism that identifies and weights features that have a more significant impact on decision-making by analyzing the feature gradient. The effectiveness of C-FA and its competitiveness against existing state-of the-art techniques are confirmed through extensive experiments on six representative networks including PointNet, PointNet++, DGCNN, PointConv, PCT, and Mamba3D.
- 13 May 2025
- Published by Springer Nature
- p. 316-334
Enhancing Knowledge Tracing via Random Layer-Wise Adversarial Training
- 13 May 2025
- Published by Springer Nature
- p. 316-334
Enhancing Knowledge Tracing via Random Layer-Wise Adversarial Training
- 20 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 314
Building robust deep recommender systems: Utilizing a weighted adversarial noise propagation framework with robust fine-tuning modules
- 20 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 314
Building robust deep recommender systems: Utilizing a weighted adversarial noise propagation framework with robust fine-tuning modules
- Open Access
- 14 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (2) , 1-41
A Comprehensive Understanding of the Impact of Data Augmentation on the Transferability of 3D Adversarial Examples
3D point cloud classifiers exhibit vulnerability to imperceptible perturbations, which poses a serious threat to the security and reliability of deep learning models in practical applications, making the robustness evaluation of deep 3D point cloud models increasingly important. Due to the difficulty in obtaining model parameters, black-box attacks have become a mainstream means of assessing the adversarial robustness of 3D classification models. The core of improving the transferability of adversarial examples generated by black-box attacks is to generate better generalized adversarial examples, where data augmentation has become one of the popular approaches. In this article, we employ five mainstream attack methods and combine six data augmentation strategies, namely point dropping, flipping, rotating, scaling, shearing, and translating, in order to comprehensively explore the impact of these strategies on the transferability of adversarial examples. Our research reveals that data augmentation methods generally improve the transferability of the adversarial examples, and the effect is better when the methods are stacked. The interaction between data augmentation methods, model characteristics, attack, and defense strategies collectively determines the transferability of adversarial examples. In order to comprehensively understand and improve the effectiveness of adversarial examples, it is necessary to comprehensively consider these complex interrelationships.
- 14 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (2) , 1-41
Open AccessA Comprehensive Understanding of the Impact of Data Augmentation on the Transferability of 3D Adversarial Examples
3D point cloud classifiers exhibit vulnerability to imperceptible perturbations, which poses a serious threat to the security and reliability of deep learning models in practical applications, making the robustness evaluation of deep 3D point cloud models increasingly important. Due to the difficulty in obtaining model parameters, black-box attacks have become a mainstream means of assessing the adversarial robustness of 3D classification models. The core of improving the transferability of adversarial examples generated by black-box attacks is to generate better generalized adversarial examples, where data augmentation has become one of the popular approaches. In this article, we employ five mainstream attack methods and combine six data augmentation strategies, namely point dropping, flipping, rotating, scaling, shearing, and translating, in order to comprehensively explore the impact of these strategies on the transferability of adversarial examples. Our research reveals that data augmentation methods generally improve the transferability of the adversarial examples, and the effect is better when the methods are stacked. The interaction between data augmentation methods, model characteristics, attack, and defense strategies collectively determines the transferability of adversarial examples. In order to comprehensively understand and improve the effectiveness of adversarial examples, it is necessary to comprehensively consider these complex interrelationships.
- 6 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
IFM: Integrating and fine-tuning adversarial examples of recommendation system under multiple models to enhance their transferability
- 6 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
IFM: Integrating and fine-tuning adversarial examples of recommendation system under multiple models to enhance their transferability
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 24597-24607
Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning
Shiji Yang, Shu Zhao, Congyao Mei, Zhen Yang, Jie Chen, Fulan Qian, Zhen Duan, Yanping Zhang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 24597-24607
Open AccessForget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning
Shiji Yang, Shu Zhao, Congyao Mei, Zhen Yang, Jie Chen, Fulan Qian, Zhen Duan, Yanping Zhang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.