Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.6
Journals
Electronics
Special Issues
Adversarial Attacks and Defenses in AI Safety/Reliability
share announcement

Adversarial Attacks and Defenses in AI Safety/Reliability

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 February 2025 | Viewed by 709

Special Issue Editors

Dr. Hong Liu

E-Mail Website
Guest Editor
The Institute for Datability Science (IDS), Osaka University, Osaka 565-0871, Japan
Interests: computer vision and machine learning; especially in AI safety/reliability; deep learning; multimodal ML; AI ethics; large-scale image retrieval
Special Issues, Collections and Topics in MDPI journals
Dr. Bowen Wang

E-Mail Website
Guest Editor
The Institute for Datability Science (IDS), Osaka University, Osaka 565-0871, Japan
Interests: computer vision; explainable AI; city perception; medical AI

Special Issue Information

Dear Colleagues,

Deep learning (DL) is at the heart of the current rise of artificial intelligence. Meanwhile, machine learning (ML) models have made significant strides in various domains, revolutionizing industries and enabling groundbreaking applications. However, with the growing reliance on these models, concerns surrounding their vulnerability to adversarial attacks have also intensified, such as in images. Despite advances in computing power, pixel resolution, and frame rate, perturbations are often too small to be perceptible, yet they completely fool the deep learning models. On some occasions, data anonymization is necessary as it reduces the risk of unintended disclosure when sharing data between countries, industries, and even departments within the same company. It also reduces opportunities for identity theft to occur. Hence, advanced techniques in this area have attracted increasing attention from both machine learning and security communities and have become a hot research topic in recent years.

This Commemorative Special Issue welcomes the submission of papers based on original research about adversarial and federated machine learning. Historical reviews, as well as perspective analyses for the future in this field of research, will also be taken into consideration. Research areas may include (but are not limited to) the following:

  1. Foundations of understanding adversarial machine learning;
  2. Theories and algorithms for adversarial attacking;
  3. Robustness certification and property verification techniques;
  4. Adversarial defense against different adversarial attacks;
  5. Adversarial detection techniques against various adversarial attacks;
  6. Empirical analysis of adversarial machine learning;
  7. Novel applications of adversarial machine learning;
  8. Formal theory for adversarial leaning.

Dr. Hong Liu
Dr. Bowen Wang
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. Electronics 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 2400 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

  • adversarial defense
  • adversarial examples detection
  • adversarial machine learning
  • deep learning
  • AI (artificial intelligence) safety and reliability
  • trustworthy AI
  • privacy-preserving AI

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.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices 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

13 pages, 1781 KiB  
Article
A3GT: An Adaptive Asynchronous Generalized Adversarial Training Method
by Zeyi He, Wanyi Liu, Zheng Huang, Yitian Chen and Shigeng Zhang
Electronics 2024, 13(20), 4052; https://doi.org/10.3390/electronics13204052 - 15 Oct 2024
Viewed by 568
Abstract
Adversarial attack methods can significantly improve the classification accuracy of deep learning models, but research has found that although most deep learning models with defense methods still show good classification accuracy in the face of various adversarial attack attacks, the improved robust models [...] Read more.
Adversarial attack methods can significantly improve the classification accuracy of deep learning models, but research has found that although most deep learning models with defense methods still show good classification accuracy in the face of various adversarial attack attacks, the improved robust models have a significantly lower classification accuracy when facing clean samples compared to themselves without using defense methods. This means that while improving the model’s adversarial robustness, it is necessary to find a defense method to balance the accuracy of clean samples (clean accuracy) and the accuracy of adversarial samples (robust accuracy). Therefore, in this work, we propose an Adaptive Asynchronous Generalized Adversarial Training (A3GT) method, which is an improvement over the existing Generalist method. It employs an adaptive update strategy without the need for extensive experiments to determine the optimal starting iteration for global updates. The experimental results show that compared with other advanced methods, A3GT can achieve a balance between clean sample classification accuracy and robust classification accuracy while improving the model’s adversarial robustness. Full article
(This article belongs to the Special Issue Adversarial Attacks and Defenses in AI Safety/Reliability)
►▼ 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