Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
AI Security and Edge Computing in Distributed Edge Systems
share announcement

AI Security and Edge Computing in Distributed Edge Systems

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 31 May 2025 | Viewed by 1455

Special Issue Editors

Dr. Kongyang Chen

E-Mail Website
Guest Editor
Institutes of Artificial Intelligence, Guangzhou University, Guangzhou 510006, China
Interests: machine learning security; Internet of Things; edge computing
Special Issues, Collections and Topics in MDPI journals
Dr. Hongyang Yan

E-Mail Website
Guest Editor
Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, China
Interests: machine learning; privacy preserving
Dr. Yatie Xiao

E-Mail Website
Guest Editor Assistant
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China
Interests: AI security; deep learning; distributed learning

Special Issue Information

Dear Colleagues,

The advent of edge computing has revolutionized the way we process and analyze data, bringing computational power closer to the data source. This paradigm shift has enabled numerous applications across various domains, from smart cities to industrial automation. With the integration of Artificial Intelligence (AI) techniques into edge systems, the potential for innovation and efficiency gains is vast. However, this integration also introduces significant security challenges that must be addressed to ensure the robustness and reliability of these systems. This Special Issue aims to provide a platform for researchers and practitioners to disseminate their latest findings, exchange ideas, and discuss challenges and solutions related to the security aspects of AI in distributed edge environments.

Topics of interest include, but are not limited to, the following:

  • Security threats and vulnerabilities in AI-enabled edge systems;
  • Privacy-preserving AI techniques for edge computing;
  • Secure and efficient distributed machine learning algorithms for edge devices;
  • Trustworthiness and integrity of AI models deployed at the edge;
  • Secure communication protocols for edge-to-cloud and edge-to-edge interactions;
  • Threat modeling and risk assessment in edge computing environments;
  • Intrusion detection and prevention systems for edge networks;
  • Hardware-based security solutions for edge devices;
  • Federated learning and secure aggregation in edge computing;
  • Regulatory and ethical considerations in securing AI at the edge.

Dr. Kongyang Chen
Dr. Hongyang Yan
Guest Editors

Dr. Yatie Xiao
Guest Editor Assistant

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

  • edge computing
  • artificial intelligence
  • AI security
  • distributed systems
  • privacy preservation
  • machine learning
  • distributed learning
  • federated learning
  • edge-to-cloud communication
  • large-language model

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

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

Research

17 pages, 2997 KiB  
Article
Private Data Protection with Machine Unlearning in Contrastive Learning Networks
by Kongyang Chen, Zixin Wang and Bing Mi
Mathematics 2024, 12(24), 4001; https://doi.org/10.3390/math12244001 - 20 Dec 2024
Viewed by 829
Abstract
The security of AI models poses significant challenges, as sensitive user information can potentially be inferred from the models, leading to privacy breaches. To address this, machine unlearning methods aim to remove specific data from a trained model, effectively eliminating the training traces [...] Read more.
The security of AI models poses significant challenges, as sensitive user information can potentially be inferred from the models, leading to privacy breaches. To address this, machine unlearning methods aim to remove specific data from a trained model, effectively eliminating the training traces of those data. However, most existing approaches focus primarily on supervised learning scenarios, leaving the unlearning of contrastive learning models underexplored. This paper proposes a novel fine-tuning-based unlearning method tailored for contrastive learning models. The approach introduces a third-party dataset to ensure that the model’s outputs for forgotten data align with those of the third-party dataset, thereby removing identifiable training traces. A comprehensive loss function is designed, encompassing three objectives: preserving model accuracy, constraining gradients to make forgotten and third-party data indistinguishable, and reducing model confidence on the third-party dataset. The experimental results demonstrate the effectiveness of the proposed method. Membership inference attacks conducted before and after unlearning show that the forgotten data’s prediction distribution becomes indistinguishable from that of the third-party data, validating the success of the unlearning process. Moreover, the proposed method achieves this with minimal performance degradation, making it suitable for practical applications in privacy-preserving AI. Full article
(This article belongs to the Special Issue AI Security and Edge Computing in Distributed Edge Systems)
►▼ Show Figures

Figure 1

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