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


Yulin Wu has a total of 67 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • NegLLM: Enhancing Strategic LLM Negotiation Agents with Case-Based Reasoning

    by Ruoke Wang, Tianzi Ma, Yulin Wu, Jiajia Zhang, Xuan Wang

  • Query-based model extraction attack: A survey

    by Yulin Wu, Zelin Li, Yuxin Wang, Aiwei Liu, Shuhan Qi, Bin Chen, Xuan Wang

  • Open Access

    AWMA-MoE: Attention-Guided Watermark Adapter with MoE for Latent Diffusion Models

    by Yicheng Huang, Xinyu Xiao, Jian Zhang, Shuhan Qi, Yulin Wu, Xuan Wang

  • CGNNStealer: Cooperative data-free model extraction attack on graph neural networks

    by Yulin Wu, Zelin Li, Aiwei Liu, Xiaozhen Sun, Yuxin Wang, Junyi Li, Xuan Wang


  • Dual Feature Fusion for Incomplete Multi-View Multi-Label Learning

    by Xinyu Xiao, Shuhan Qi, Yulin Wu, Bin Chen, Chao Xing, Xuan Wang

    Multi-view Multi-label Learning (MVML) aims to leverage multi-view information from input samples to achieve accurate predictions of multiple labels. Unfortunately, most existing MVML methods operate under the assumption of data completeness, which makes them ineffective in practical scenarios involving missing views or uncertain labels. Recent methods address incomplete data, but few approaches handle scenarios where both views and labels are missing. To address this challenge, we propose a Dual-view Feature-guided Fusion Learning (DFFL) framework. DFFL considers both view-specific unique features and inter-view consistent features. Specifically, DFFL constructs view-uniqueness contrastive learning to ensure that features within the same view maintain high semantic relevance under the condition of view missing, while the semantics between different views are different. Unlike previous methods, DFFL assumes that label relevance can be reversely mapped to high-dimensional features. By establishing View-consistency learning, the mutual information in the shared embedding space is maximized to achieve consistent feature alignment. In particular, DFFL minimizes the conditional entropy of the marginal distribution of multi-view features through dual prediction, thereby deriving the maximum joint distribution of feature fusion and combining the missing view index matrix to achieve feature fusion. This process can effectively alleviate the fusion feature suppression existing in previous methods. Finally, the missing label index matrix is combined with the fusion feature to complete the classification task. We validate the framework on five widely used datasets, and experimental results demonstrate that our approach achieves superior performance compared to state-of-the-art methods. Ablation studies further validated the effectiveness of each component in DFFL.

  • Open Access

    Efficient Last-Iterate Convergence in Regret Minimization via Adaptive Reward Transformation

    by Hang Ren, Yulin Wu, Shuhan Qi, Jiajia Zhang, Xiaozhen Sun, Tianzi Ma, Xuan Wang

    Regret minimization is a powerful method for finding Nash equilibria in Normal-Form Games (NFGs) and Extensive-Form Games (EFGs), but it typically guarantees convergence only for the average strategy. However, computing the average strategy requires significant computational resources or introduces additional errors, limiting its practical applicability. The Reward Transformation (RT) framework was introduced to regret minimization to achieve last-iterate convergence through reward function regularization. However, it faces practical challenges: its performance is highly sensitive to manually tuned parameters, which often deviate from theoretical convergence conditions, leading to slow convergence, oscillations, or stagnation in local optima. Inspired by previous work, we propose an adaptive technique to address these issues, ensuring better consistency between theoretical guarantees and practical performance for RT Regret Matching (RTRM), RT Counterfactual Regret Minimization (RTCFR), and their variants in solving NFGs and EFGs more effectively. Our adaptive methods dynamically adjust parameters, balancing exploration and exploitation while improving regret accumulation, ultimately enhancing asymptotic last-iterate convergence and achieving linear convergence. Experimental results demonstrate that our methods significantly accelerate convergence, outperforming state-of-the-art algorithms.

  • Improved belief propagation decoding algorithm based on decoupling representation of Pauli operators for quantum stabilizer codes

    by Zhengzhong Yi, Zhipeng Liang, Jiahan Chen, Kaixin Zhong, Yulin Wu, Zhou Fang, Xuan Wang


  • Open Access

    Communication Efficient Secure Three-Party Computation Using Lookup Tables for RNN Inference

    by Yulin Wu, Chuyi Liao, Xiaozhen Sun, Yuyun Shen, Tong Wu

    Many leading technology companies currently offer Machine Learning as a Service Platform, enabling developers and organizations to access the inference capabilities of pre-trained models via API calls. However, due to concerns over user data privacy, inter-enterprise competition, and legal and regulatory constraints, directly utilizing pre-trained models in the cloud for inference faces security challenges. In this paper, we propose communication-efficient secure three-party protocols for recurrent neural network (RNN) inference. First, we design novel three-party secret-sharing protocols for digit decomposition, B2A conversion, enabling efficient transformation of secret shares between Boolean and arithmetic rings. Then, we propose the lookup table-based secure three-party protocol. Unlike the intuitive way of directly looking up tables to obtain results, we compute the results by utilizing the inherent mathematical properties of binary lookup tables, and the communication complexity of the lookup table protocol is only related to the output bit width. We also design secure three-party protocols for key functions in the RNN, including matrix multiplication, sigmoid function, and Tanh function. Our protocol divides the computation into online and offline phase, and places most of the computations locally. The theoretical analysis shows that the communication round of our work was reduced from four rounds to one round. The experiment results show that compared with the current SOTA-SIRNN, the online communication overhead of sigmoid and tanh functions decreased by 80.39% and 79.94%, respectively.


  • Open Access

    On the Exploration of Quantum Polar Stabilizer Codes and Quantum Stabilizer Codes with High Coding Rate

    by Zhengzhong Yi, Zhipeng Liang, Yulin Wu, Xuan Wang

    Inspired by classical polar codes, whose coding rate can asymptotically achieve the Shannon capacity, researchers are trying to find their analogs in the quantum information field, which are called quantum polar codes. However, no one has designed a quantum polar coding scheme that applies to quantum computing yet. There are two intuitions in previous research. The first is that directly converting classical polar coding circuits to quantum ones will produce the polarization phenomenon of a pure quantum channel, which has been proved in our previous work. The second is that based on this quantum polarization phenomenon, one can design a quantum polar coding scheme that applies to quantum computing. There are several previous work following the second intuition, none of which has been verified by experiments. In this paper, we follow the second intuition and propose a more reasonable quantum polar stabilizer code construction algorithm than any previous ones by using the theory of stabilizer codes. Unfortunately, simulation experiments show that even the stabilizer codes obtained from this more reasonable construction algorithm do not work, which implies that the second intuition leads to a dead end. Based on the analysis of why the second intuition does not work, we provide a possible future direction for designing quantum stabilizer codes with a high coding rate by borrowing the idea of classical polar codes. Following this direction, we find a class of quantum stabilizer codes with a coding rate of 0.5, which can correct two of the Pauli errors.


  • Open Access

    Privacy-Preserving Distributed Machine Learning Made Faster

    by Zoe L. Jiang, Jiajing Gu, Hongxiao Wang, Yulin Wu, Junbin Fang, Siu-Ming Yiu, Wenjian Luo, Xuan Wang

    With the development of machine learning, it is difficult for a single server to process all the data. So machine learning tasks need to be spread across multiple servers, turning the centralized machine learning into a distributed one. Multi-key homomorphic encryption is one of the suitable candidates to solve the problem. However, the most recent result of the Multi-key homomorphic encryption scheme (MKTFHE) only supports the NAND gate. Although it is Turing complete, it requires efficient encapsulation of the NAND gate to further support mathematical calculation. This paper designs and implements a series of operations on positive and negative integers accurately. First, we design basic bootstrapped gates, the efficiency of which is times that the number of using NAND to build. Second, we construct practical k-bit complement mathematical operators based on our basic binary bootstrapped gates. The constructed created can perform addition, subtraction, multiplication, and division on both positive and negative integers. Finally, we demonstrated the generality of the designed operators by achieving a distributed privacy-preserving machine learning algorithm, i.e. linear regression with two different solutions. Experiments show that the consumption time of the operators built with our gate is about 50 ∼ 70% shorter than built directly with NAND gate and the iteration time of linear regression with our gates is 66.7% shorter than with NAND gate directly.