Xiao-Kai Cao

Xiao-Kai Cao

Auto-generated profile, based on publicly available information

Xiao-Kai Cao

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 January 2023 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
XCXiao-Kai Cao
Xiao-Kai Cao
CWChang-Dong Wang
Chang-Dong Wang
JLJianhuang Lai
Jianhuang Lai
QHQiong Huang
Qiong Huang
CCC.L. Philip Chen
C.L. Philip Chen
Multiparty learning is an indispensable technique to improve the learning performance via integrating data from multiple parties. Unfortunately, directly integrating multiparty data could not meet the privacy-preserving requirements, which then induces the development of privacy-preserving machine learning (PPML), a key research task in multiparty learning. Despite this, the existing PPML methods generally cannot simultaneously meet multiple requirements, such as security, accuracy, efficiency, and application scope. To deal with the aforementioned problems, in this article, we present a new PPML method based on the secure multiparty interactive protocol, namely, the multiparty secure broad learning system (MSBLS) and derive its security analysis. To be specific, the proposed method employs the interactive protocol and random mapping to generate the mapped features of data, and then uses efficient broad learning to train the neural network classifier. To the best of our knowledge, this is the first attempt for privacy computing method that jointly combines secure multiparty computing and neural network. Theoretically, this method can ensure that the accuracy of the model will not be reduced due to encryption, and the calculation speed is very fast. Three classical datasets are adopted to verify our conclusion.

1 January 2021 in Nonlinear Analysis Modelling and Control
Verified
Journal Article
Open access
PDF file
XCXiaokai Cao
Xiaokai Cao
Michal FečkanMichal Fečkan
Michal Fečkan
DSDong Shen
Dong Shen
JWJinRong Wang
JinRong Wang
In this paper, we adopt D-type and PD-type learning laws with the initial state of iteration to achieve uniform tracking problem of multi-agent systems subjected to impulsive input. For the multi-agent system with impulse, we show that all agents are driven to achieve a given asymptotical consensus as the iteration number increases via the proposed learning laws if the virtual leader has a path to any follower agent. Finally, an example is illustrated to verify the effectiveness by tracking a continuous or piecewise continuous desired trajectory.

14 March 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
XCXiao-Kai Cao
Xiao-Kai Cao
MCMan-Sheng Chen
Man-Sheng Chen
CWChang-Dong Wang
Chang-Dong Wang
JLJianhuang Lai
Jianhuang Lai
QHQiong Huang
Qiong Huang
CCC.L. Philip Chen
C.L. Philip Chen
Distributed computing as a widely concerned research direction needs to use the data training model of users, making the security of users' private data become a challenging problem to be solved. At present, federated learning is the mainstream research method to solve this problem. However, federated learning is not good at distributed training on streaming data. In real scenarios, the client's data is usually continuously updated streaming data. In this paper, we propose Dynamic Secure Multi Broad Network (DSMBN), which is a novel privacy computing framework completely different from federated learning. In DSMBN, we design three interactive communication protocols to handle streaming data in different scenarios. The function of the protocol is to use random mapping to encrypt data during the interaction. The protocol ensures that the client's original data does not leave the local server when generating mapped features. The central server uses the resulting mapped features (essentially encrypted data) instead of the original data to train machine learning models. In theoretical analysis, we analyze the first protocol's security, communication costs, and computational complexity. In the experiment, we design seven experimental scenarios, including quantity balance, Non-IID data distribution and streaming data, and compare them with several mainstream privacy protection machine learning methods. The experimental results show that compared with centralized training without privacy protection, DSMBN can achieve the same test accuracy under the premise of protecting private data security. Compared with mainstream federated learning methods, DSMBN can achieve higher accuracy in the Non-IID scenarios and save computing time and communication resources.

15 April 2026 in Information Fusion
Verified
Journal Article
Closed access
XCXiaosha Cai
Xiaosha Cai
MCMan-Sheng Chen
Man-Sheng Chen
YLYihong Lu
Yihong Lu
CWChang-Dong Wang
Chang-Dong Wang
XCXiaokai Cao
Xiaokai Cao
HZHaizhang Zhang
Haizhang Zhang

1 May 2019
Verified
Conference Paper
Closed access
YCYu Chen
Yu Chen
JWJinRong Wang
JinRong Wang
XCXiaoKai Cao
XiaoKai Cao
The article study the ILC for nonlinear Stieltjes differential equations. We establish sufficient conditions and prove Stieltjes D-type and Stieltjes PD-type learning algorithms convergence results for such equation. The theoretical results are demonstrated using the numerical examples in the end.

22 June 2022 in arXiv
Verified
Preprint
Open access
PDF file
XCXiao-Kai Cao
Xiao-Kai Cao
CWChang-Dong Wang
Chang-Dong Wang
JLJianhuang Lai
Jianhuang Lai
QHQiong Huang
Qiong Huang
CCC. L. Philip Chen
C. L. Philip Chen
Multi-party learning is an indispensable technique for improving the learning performance via integrating data from multiple parties. Unfortunately, directly integrating multi-party data would not meet the privacy preserving requirements. Therefore, Privacy-Preserving Machine Learning (PPML) becomes a key research task in multi-party learning. In this paper, we present a new PPML method based on secure multi-party interactive protocol, namely Multi-party Secure Broad Learning System (MSBLS), and derive security analysis of the method. The existing PPML methods generally cannot simultaneously meet multiple requirements such as security, accuracy, efficiency and application scope, but MSBLS achieves satisfactory results in these aspects. It uses interactive protocol and random mapping to generate the mapped features of data, and then uses efficient broad learning to train neural network classifier. This is the first privacy computing method that combines secure multi-party computing and neural network. Theoretically, this method can ensure that the accuracy of the model will not be reduced due to encryption, and the calculation speed is very fast. We verify this conclusion on three classical datasets.