Trust evaluation is a process to quantify trust by analyzing the data related to the factors that affect trust. It has been widely applied in many fields to facilitate decision making, system entity collaboration and security establishment, e.g., social networking, digital communications, e-commerce, cloud services, Peer-to-Peer networking, and so on. Nowadays, trust evaluation has become a useful technique that has benefited many emerging areas by playing as a significant compensation to other security technologies.
With the rapid development of cyber systems and the huge volumes of data bursted in it, trust evaluation is evolving from simple mathematical calculation to data analytics based on data fusion, e.g., machine learning. Traditional trust evaluation methods determine trust by aggregating trust factors through weighting and relevant calculations. They become infeasible facing large amount of data with a complex structure. In response to this problem, many researchers suggested using data fusion to make trust evaluation intelligent and accurate. Comparing with the traditional methods, using data fusion for trust evaluation has some irreplaceable advantages. First, it can overcome “cold start” and “zero knowledge” problems. By training a model with available trust-related feature data, trust evaluation can be performed even though some valuable data are missed. Second, the recent advance of data fusion can help evaluating trust in an accurate way, especially when we need to handle enormous data with a complex structure. Third, data fusion can precisely simulate human decision making with regard to trust evaluation, thus evaluation results can be easily explained and accepted by human-beings.
However, a number of new challenges are raised in data fusion for trust evaluation caused by practical demands and limitations of current data fusion technologies. First, a generic model for trust evaluation based on data fusion is still missed and hard to achieve. Second, trust evaluation requests a fine-grained evaluation result, which is hard to achieve with machine learning since it treats trust evaluation as a classification problem with two or a limited number of categories such as trusted and distrusted. Third, existing methods generally do not consider privacy protection on the data used for evaluation and seldom concern the robustness of evaluation. True data discovery and attack tracing are seldom studied. Last but not the least, most of the existing methods do not pay special attention to evaluation efficiency. This greatly impacts their applicability in practice.
This special issue aims to bring together researchers and practitioners to discuss various aspects of data fusion for trust evaluation, explore key theories and technologies, investigate technology enablers and innovate new solutions for overcoming major challenges in this research field.
Manuscripts (which should be original and not previously published either in full or in part or presented even in a more or less similar form at any other forum) covering unpublished research that report the advances in multimodality data fusion in neuroimaging are invited.
The manuscript will be judged solely on the basis of new contributions excluding the contributions made in earlier publications. Contributions should be described in sufficient detail to be reproducible on the basis of the material presented in the paper and the references cited therein.
Topics appropriate for this special issue include (but are not necessarily limited to):
New theories and methods of data fusion for trust evaluation
Clustering analysis for trust evaluation
Machine learning, data mining and fusion related to trust evaluation
Adversary learning in trust evaluation
New models of trust evaluation based on data fusion
Multimodal data fusion for trust evaluation based on machine learning
Fragment knowledge fusion for trust evaluation
Data fusion trust, security and privacy in trust evaluation
True value discovery and attack tracing in trust evaluation and management
Novel datasets and benchmarks for trust evaluation
Data fusion for trust, security and privacy
Please prepare your paper along with all the supplementary materials for your submission. The papers submitted to this special issue must be original. Besides that, they must not be published, “under review”, or even be submitted in any other journal, conference, or workshop. Papers will be peer-reviewed by at least three independent reviewers and will be chosen based on contributions including their originality, scientific quality as well as their suitability to this special issue. The journal editors will make the final decision on which papers will be accepted.
Authors must ensure that you carefully read the guide for authors before submitting your papers. The guide for authors and link for online submission is available on the Information Fusion homepage at: https://www.journals.elsevier.com/information-fusion. Please select “SI: DFTE” when you reach the “Article Type” step when submitting your papers. For any inquiry or question regarding this special issue, authors may contact directly via email to Zheng Yan at email@example.com.
Zheng Yan, Xidian University, China & Aalto University, Finland
Qinghua Zheng, Xi’an Jiaotong University, China
Laurence T. Yang, St Francis Xavier University, Canada & Huazhong University of Science and Technology, China
Robert H. Deng, Singapore Management University, Singapore
Deadline for Submission: December 1. 2020