Network Intrusion Detection and Attack Identification

Dear Colleagues,

Network security is becoming more and more complicated and challenging than ever with the emergence of the IoT, 5G and beyond networks. For example, effectively handling massive network traffic data and detecting new attacks are still challenging problems. As artificial intelligence has been tremendously successfully in computer vision, robotics, natural language processing, etc., many propose network intrusion detection and attack identification based on artificial intelligence to solve the problems. Furthermore, many of these solutions can outperform traditional methods, e.g., rule-based, signature-based, etc. However, AI-based network intrusion and attack identification solutions still encounter issues such as robustness, reliability, explainability, trustworthiness, adaptability, etc. Attackers may use adversarial techniques (e.g., data poisoning and backdoor attacks) to fool AI-based models. Many AI-based solutions are black-box ones, which means how the solutions make the decisions are not evident to the user. Therefore, reliable network intrusion detection and attack identification need to be able to explain the result to the user. Many AI-based solutions are still not robust enough to detect sophisticated network attacks exploiting zero-day vulnerabilities due to the overfitting problem. In other words, the models cannot perform well using traffic data with slightly different characteristics. One way to solve the problem may be to use transfer learning and domain adaption to make AI-based models more adaptable to varying network data characteristics. Lastly, effective AI-based network intrusion detection and attack identification methods can also detect evasive attacks (e.g., using obfuscation/encryption techniques in payload data, traffic fragmentation, etc.) using attack types.

This Special Issue encourages artificial intelligence and security researchers and practitioners to submit their novelty solutions for the robustness, reliability, explainability, trustworthiness, and adaptability of AI-based Network Intrusion Detection and Attack Identification models with corresponding network traffic datasets.

Topics of interest include, but are not limited to:

• AI-based Network Attack Detection, Classification and Mitigation;
• Threat Detection and Mitigation using MITRE ATT&CK;
• Robust and Reliable Attack Detection and Identification;
• AI-based Network Attack Generation and Defense;
• Adversarial Learning for Network Intrusion Detection;
• Interpretable Network Intrusion Detection;
• Next-generation of Network Intrusion Detection and Attack Identification Systems;
• Unsupervised Network Anomaly Detection;
• Network Anomaly Detection with Domain Adaption;
• Network Anomaly Detection based on Transfer Learning;
• Network Anomaly Detection using Federated Learning and Transfer Learning.

Dr. Sin Gee Teo
Dr. Rongxing Lu
Guest Editors

Dr. Ruitao Feng
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. 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.

• network attack
• attack type
• ai-based model
• adversarial technique
• evasive attack