Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Advanced Analyses and Algorithms for Trustworthy AI Systems and Applications
share announcement

Advanced Analyses and Algorithms for Trustworthy AI Systems and Applications

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Computational and Applied Mathematics".

Deadline for manuscript submissions: 31 October 2024 | Viewed by 3188

Special Issue Editors

Prof. Dr. Liang Hu

E-Mail Website
Guest Editor
College of Electronics and Information Engineering, Tongji University, 4800 Cao'an Highway, Shanghai 201804, China
Interests: trustworthy machine learning; recommender systems; lifelong learning; data science
Prof. Dr. Jian Cao

E-Mail Website
Guest Editor
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Interests: recommender systems; service computing; intelligent data analytics
Special Issues, Collections and Topics in MDPI journals
Dr. Chaochao Chen

E-Mail Website
Guest Editor
College of Computer Science and Technology, Zhejiang University, 866 Yuhangtang Rd, Xihu, Hangzhou 310027, China
Interests: privacy-preserving machine learning; federated learning; trustworthy machine learning

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) has had a revolutionary influence on modern human society and has been playing an irreplaceable role in many aspects of our lives. Modern life is full of interactions with AI applications, such as e-business, finance, fashion, transportation, and healthcare. However, increasing forms of attack on AI systems have been witnessed with the rapid development of AI applications in every domain. For example, AI algorithms can cause biased and unfair recommendations in e-business; AIGC (AI-generated content) systems may produce indecent and sexist content, which can result in negative social impacts; AI financial applications may carry the risk of leaking user privacy and producing unexpected trading operations; the features generated by AI models can potentially be hacked to reconstruct private data and sensitive information.

All the above vulnerabilities of existing AI systems can lead to serious social and economic consequences. Therefore, building trustworthy AI systems and applications has become an inescapable challenge in both academia and industry. In this Special Issue, we encourage authors to target the construction of AI systems and applications, considering trustworthiness in various dimensions, such as security, robustness, non-discrimination, fairness, explainability, privacy, auditability, accountability, and environmental well-being.

The Special Issue invites submissions on all topics of analyses, algorithms, and models for trustworthy AI systems and applications, including, but not limited to, federated learning, privacy-persevering computation, causal learning, natural language processing, computer vision, graph neural networks, social network analysis, biometric data analysis, recommender systems, facial and voice recognition systems, autonomous driving systems, financial trading systems, power and energy management systems, and healthcare information systems.

Prof. Dr. Liang Hu
Prof. Dr. Jian Cao
Dr. Chaochao Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • trustworthy algorithms
  • trustworthy machine learning
  • trustworthy AI systems
  • trustworthy AI applications
  • personal privacy
  • data security

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

22 pages, 5397 KiB  
Article
Challenges and Countermeasures of Federated Learning Data Poisoning Attack Situation Prediction
by Jianping Wu, Jiahe Jin and Chunming Wu
Mathematics 2024, 12(6), 901; https://doi.org/10.3390/math12060901 - 19 Mar 2024
Viewed by 630
Abstract
Federated learning is a distributed learning method used to solve data silos and privacy protection in machine learning, aiming to train global models together via multiple clients without sharing data. However, federated learning itself introduces certain security threats, which pose significant challenges in [...] Read more.
Federated learning is a distributed learning method used to solve data silos and privacy protection in machine learning, aiming to train global models together via multiple clients without sharing data. However, federated learning itself introduces certain security threats, which pose significant challenges in its practical applications. This article focuses on the common security risks of data poisoning during the training phase of federated learning clients. First, the definition of federated learning, attack types, data poisoning methods, privacy protection technology and data security situational awareness are summarized. Secondly, the system architecture fragility, communication efficiency shortcomings, computing resource consumption and situation prediction robustness of federated learning are analyzed, and related issues that affect the detection of data poisoning attacks are pointed out. Thirdly, a review is provided from the aspects of building a trusted federation, optimizing communication efficiency, improving computing power technology and personalized the federation. Finally, the research hotspots of the federated learning data poisoning attack situation prediction are prospected. Full article
(This article belongs to the Special Issue Advanced Analyses and Algorithms for Trustworthy AI Systems and Applications)
►▼ Show Figures

Figure 1

17 pages, 3642 KiB  
Article
A Secure Multi-Party Computation Protocol for Graph Editing Distance against Malicious Attacks
by Xin Liu, Jianwei Kong, Lu Peng, Dan Luo, Gang Xu, Xiubo Chen and Xiaomeng Liu
Mathematics 2023, 11(23), 4847; https://doi.org/10.3390/math11234847 - 01 Dec 2023
Viewed by 767
Abstract
The secure computation of the graph structure is an important element in the field of secure calculation of graphs, which is important in querying data in graphs, since there are no algorithms for the graph edit distance problem that can resist attacks by [...] Read more.
The secure computation of the graph structure is an important element in the field of secure calculation of graphs, which is important in querying data in graphs, since there are no algorithms for the graph edit distance problem that can resist attacks by malicious adversaries. In this paper, for the problem of secure computation of similarity edit distance of graphs, firstly, the encoding method applicable to the Paillier encryption algorithm is proposed, and the XOR operation scheme is proposed according to the Paillier homomorphic encryption algorithm. Then, the security algorithm under the semi-honest model is designed, which adopts the new encoding method and the XOR operation scheme. Finally, for the malicious behaviors that may be implemented by malicious participants in the semi-honest algorithm, using the hash function, a algorithm for secure computation of graph editing distance under the malicious model is designed, and the security of the algorithm is proved, and the computational complexity and the communication complexity of the algorithm are analyzed, which is more efficient compared with the existing schemes, and has practical value. The algorithm designed in this paper fills the research gap in the existing literature on the problem of graph edit distance and contributes to solving the problem. Full article
(This article belongs to the Special Issue Advanced Analyses and Algorithms for Trustworthy AI Systems and Applications)
►▼ Show Figures

Figure 1

21 pages, 31983 KiB  
Article
DLPformer: A Hybrid Mathematical Model for State of Charge Prediction in Electric Vehicles Using Machine Learning Approaches
by Yaoyidi Wang, Niansheng Chen, Guangyu Fan, Dingyu Yang, Lei Rao, Songlin Cheng and Xiaoyong Song
Mathematics 2023, 11(22), 4635; https://doi.org/10.3390/math11224635 - 13 Nov 2023
Cited by 2 | Viewed by 974
Abstract
Accurate mathematical modeling of state of charge (SOC) prediction is essential for battery management systems (BMSs) to improve battery utilization efficiency and ensure a good safety performance. The current SOC prediction framework only considers battery-related features but ignores vehicle information. Additionally, in light [...] Read more.
Accurate mathematical modeling of state of charge (SOC) prediction is essential for battery management systems (BMSs) to improve battery utilization efficiency and ensure a good safety performance. The current SOC prediction framework only considers battery-related features but ignores vehicle information. Additionally, in light of the emergence of time-series Transformers (TSTs) that harness the power of multi-head attention, developing a SOC prediction model remains a significant challenge. Therefore, we introduce a new framework that integrates laboratory battery data with mathematical vehicle model features to improve the accuracy of the SOC and propose a prediction model named DLPformer, which can effectively capture variations in the SOC attributed to both trend and seasonal patterns. First, we apply Matlab/Simulink to simulate a mathematical model of electric vehicles and process the generated vehicle data with Spearman correlation analysis to identify the most relevant features, such as the mechanical losses of the electric motor, differential, and aerodynamic drag. Then, we employ a data fusion method to synchronize the heterogeneous datasets with different frequencies to capture the sudden changes in electric vehicles. Subsequently, the fused features are input into our prediction model, DLPformer, which incorporates a linear model for trend prediction and patch-input attention for seasonal component prediction. Finally, in order to effectively evaluate the extrapolation and adaptability of our model, we utilize different driving cycles and heterogeneous battery datasets for training and testing. The experimental results show that our prediction model significantly improves the accuracy and robustness of SOC prediction under the proposed framework, achieving MAE values of 0.18% and 0.10% across distinct driving cycles and battery types. Full article
(This article belongs to the Special Issue Advanced Analyses and Algorithms for Trustworthy AI Systems and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop