applsci-logo

Journal Browser

Journal Browser

Risk and Protection for Machine Learning-Based Network Intrusion

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (20 June 2024) | Viewed by 3552

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science and Information Engineering, National Taipei University, New Taipei City 237303, Taiwan
Interests: network intrusion prevention; deep learning quality; blockchain smart contracts; IoT routing

Special Issue Information

Dear Colleagues,

As the scale of network intrusion grows, machine learning models become a popular approach for intrusion detection based on their significant computation capability, especially deep learning models. Although machine learning-based intrusion detection models can detect a large range of network intrusions, it is difficult to explain the detection results because of the model’s computation complexity. Adversarial attacks can pollute the detection training model to mislead the detection results, and they are difficult to be observed. Thus, non-explainable results and adversarial attacks lead to new risks of machine learning-based intrusion detection models.

This Special Issue invites research or review papers on new advanced protections for machine learning-based intrusion detection models that explore with their new risks, such as adversarial attacks. For federal learning, if malicious clients provide the training results polluted by the adversarial attacks, the server training model is also polluted. Generative adversarial networks can generate both beneficial training samples and adversarial samples. Contrastive learning models have illustrated their self-learning capability for images, and they can be good candidates to protect the intrusion detections via self-learning. Blockchain is also a popular approach to protect against intrusion detections. These new emerging techniques can establish hybrid protection solutions for intrusion detection to prevent their new risks.

Dr. Chinyang Henry Tseng
Prof. Dr. Hsing-Chung 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. Applied Sciences 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

  • intrusion detection
  • machine learning
  • deep learning
  • adversarial attack
  • federal learning
  • generative adversarial network
  • contrastive learning
  • blockchain

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 (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

22 pages, 2298 KiB  
Article
Exploring the Efficacy of Learning Techniques in Model Extraction Attacks on Image Classifiers: A Comparative Study
by Dong Han, Reza Babaei, Shangqing Zhao and Samuel Cheng
Appl. Sci. 2024, 14(9), 3785; https://doi.org/10.3390/app14093785 - 29 Apr 2024
Viewed by 1081
Abstract
In the rapidly evolving landscape of cybersecurity, model extraction attacks pose a significant challenge, undermining the integrity of machine learning models by enabling adversaries to replicate proprietary algorithms without direct access. This paper presents a comprehensive study on model extraction attacks towards image [...] Read more.
In the rapidly evolving landscape of cybersecurity, model extraction attacks pose a significant challenge, undermining the integrity of machine learning models by enabling adversaries to replicate proprietary algorithms without direct access. This paper presents a comprehensive study on model extraction attacks towards image classification models, focusing on the efficacy of various Deep Q-network (DQN) extensions for enhancing the performance of surrogate models. The goal is to identify the most efficient approaches for choosing images that optimize adversarial benefits. Additionally, we explore synthetic data generation techniques, including the Jacobian-based method, Linf-projected Gradient Descent (LinfPGD), and Fast Gradient Sign Method (FGSM) aiming to facilitate the training of adversary models with enhanced performance. Our investigation also extends to the realm of data-free model extraction attacks, examining their feasibility and performance under constrained query budgets. Our investigation extends to the comparison of these methods under constrained query budgets, where the Prioritized Experience Replay (PER) technique emerges as the most effective, outperforming other DQN extensions and synthetic data generation methods. Through rigorous experimentation, including multiple trials to ensure statistical significance, this work provides valuable insights into optimizing model extraction attacks. Full article
(This article belongs to the Special Issue Risk and Protection for Machine Learning-Based Network Intrusion)
Show Figures

Figure 1

25 pages, 2019 KiB  
Article
Optimizing Cybersecurity Attack Detection in Computer Networks: A Comparative Analysis of Bio-Inspired Optimization Algorithms Using the CSE-CIC-IDS 2018 Dataset
by Hadi Najafi Mohsenabad and Mehmet Ali Tut
Appl. Sci. 2024, 14(3), 1044; https://doi.org/10.3390/app14031044 - 25 Jan 2024
Cited by 8 | Viewed by 1842
Abstract
In computer network security, the escalating use of computer networks and the corresponding increase in cyberattacks have propelled Intrusion Detection Systems (IDSs) to the forefront of research in computer science. IDSs are a crucial security technology that diligently monitor network traffic and host [...] Read more.
In computer network security, the escalating use of computer networks and the corresponding increase in cyberattacks have propelled Intrusion Detection Systems (IDSs) to the forefront of research in computer science. IDSs are a crucial security technology that diligently monitor network traffic and host activities to identify unauthorized or malicious behavior. This study develops highly accurate models for detecting a diverse range of cyberattacks using the fewest possible features, achieved via a meticulous selection of features. We chose 5, 9, and 10 features, respectively, using the Artificial Bee Colony (ABC), Flower Pollination Algorithm (FPA), and Ant Colony Optimization (ACO) feature-selection techniques. We successfully constructed different models with a remarkable detection accuracy of over 98.8% (approximately 99.0%) with Ant Colony Optimization (ACO), an accuracy of 98.7% with the Flower Pollination Algorithm (FPA), and an accuracy of 98.6% with the Artificial Bee Colony (ABC). Another achievement of this study is the minimum model building time achieved in intrusion detection, which was equal to 1 s using the Flower Pollination Algorithm (FPA), 2 s using the Artificial Bee Colony (ABC), and 3 s using Ant Colony Optimization (ACO). Our research leverages the comprehensive and up-to-date CSE-CIC-IDS2018 dataset and uses the preprocessing Discretize technique to discretize data. Furthermore, our research provides valuable recommendations to network administrators, aiding them in selecting appropriate machine learning algorithms tailored to specific requirements. Full article
(This article belongs to the Special Issue Risk and Protection for Machine Learning-Based Network Intrusion)
Show Figures

Figure 1

Back to TopTop