Special Issue: Deep Learning and Explainable Artificial Intelligence in Network Security

Breakthroughs in 'deep learning' via use of intermediate features in multilayer 'neural networks' and generative adversarial networks using neural networks as generative and discriminative models combined with the massive increase in computing power of GPU chips have resulted in the widespread popularity and use of 'artificial intelligence' in the past decade. The apostrophes in the previous sentence are inserted on purpose to remind the reader that learning, in the biological sense, that improves survival outcomes via biological nervous systems or intelligent decisions improving energy and resource availability are far away from what current software can hope to achieve. The purpose of this Special Issue is to bridge this gap: to develop explanations and an understanding of functioning AI/ML methods, and to develop AI/ML methods that generate outcomes with predictable properties when fed with data satisfying certain conditions for network security.

Thus, it is hoped that the Special Issue will stimulate AI that will increase efficiencies while not compromising safety, trust, fairness, predictability, and reliability when applied to systems with large energy use such as power, water, transport, or financial grids, law and government policy. As a first step towards this goal of transparency of AI algorithms, we seek papers that document the methods so that:

The results are reproducible, at least in the statistical sense;

Algorithms are provided in a common language of sequences of vector matrix algebra operations, which also underlies much deep learning in network security filed;

Conditions satisfied by data inputs, objective functions of optimization or curve fitting are explicitly listed in network security filed;

The propagation of data uncertainty to algorithmic outcomes is documented through sensitivity analysis or Monte Carlo simulations.

Potential issues of interest include the following: while there is no repeatability in general in the training of weights in deep learning or most neural networks, there is repeatability in approximating functions or decision boundaries for similar sets of input data. Such results also exist in adaptive control where there is asymptotic tracking without the convergence of parameter estimates in network security filed. Similarly, a ChatGPT-like AI needs to maintain the consistency of its conclusions, provided the inputs remain consistent. The use of AI in the law can have, for example, quantifiable goals such as the prompt compensation of the victim and long-term reformation of the criminal to higher levels of productivity rather than classical legal outcomes of punishment or retribution, which are subjective.

Network security protects communication networks and their data from unauthorised access, use, disclosure, disruption, modification, or destruction. Cryptography, as a fundamental tool, is used in various aspects of network security to achieve these goals.

Specific topics of interest include, but are not limited to:

• Cloud computing security;
• Communication technologies and protocol security;
• Cryptographic security protocols;
• Emerging cryptographic techniques;
• Federate learning;
• Hashing techniques;
• Homomorphic encryption in networks;
• Key distribution and management;
• Real-time cryptography applications;
• Trusted heterogeneous networks.

Important Dates:

Submission Deadline: November 20, 2024

First Review Notification: January 31, 2025

Revision Submission: April 30, 2025

Final Decision: May 15, 2025

Camera Ready Version: June 15, 2025

Online Publication: July 2025

The review process will comply with the standard review process of the IJNS journal. Each paper will receive at least three reviews from experts in the field.

Guest Editor.

Prof. Dr. Hang Li, email: lihang@synu.edu.cn

Northeastern University & Shenyang Normal University.

Dean of Software College in Shenyang Normal University.

Visiting professor in Northeastern University.

Director of Intelligent Information Processing Laboratory in Shenyang Normal University.

ORCID identifier : 0000-0002-1230-4007