Dear colleagues,

Our apologies if you receive multiple copies of this message.

**********************************************************************

                     CALL FOR PAPERS

         Special Issue on Generative and Explainable AI

         for Internet Traffic and Network Architectures

                 Elsevier Computer Networks

https://www.sciencedirect.com/journal/computer-networks/about/call-for-papers#generative-and-explainable-artificial-intelligence-for-internet-traffic-and-architectures

(Submission deadline: December 1, 2024)

**********************************************************************

We are pleased to announce a call for papers for a special issue of
Elsevier Computer Networks journal, focusing on the transformative potential
of generative and explainable AI in Internet traffic analysis and network

architectures. As Internet-connected devices multiply and traffic data grows

exponentially, traditional methods are increasingly challenged. This special

issue aims to highlight how generative AI can synthesize realistic traffic data,

automate network configurations, and enhance security measures. Additionally,

explainable AI can provide deeper insights into network behaviors, improving

transparency, trust, and overall network performance.

We invite you to contribute to this pioneering special issue and lead the

advancement of AI-driven innovations in Internet traffic analysis and network

architectures.

Key Topics of Interest include but are not limited to the following:

-----------------------

- Generative AI methods to synthesize realistic and diverse traffic data

- Automatic network configuration and management utilizing Generative AI

- Applications of Large Language Models (LLMs) in network traffic generation

- Prompt Engineering for LLMs in network traffic analysis, management, and security

- Generative AI for enhancing network security and intrusion detection

- Assessing the robustness and reliability of Generative AI in network

  management, including standardized benchmarks and datasets

- Explainable AI techniques for network traffic analysis and management tools

- Human-in-the-loop AI and the integration of interpretability into AI-driven

  traffic analysis

- Ensuring fairness, accountability, and transparency in AI applications for

  networking

- Real-world applications and case studies showcasing Generative and Explainable

  AI in network traffic analysis, management, and security

- Bridging the gap between network data explanation and actionable

  interpretability

- Techniques for improving the trust and practical use of data-driven network

  analysis methods

Guest Editors:

--------------

- Antonio Montieri, PhD - Università degli Studi di Napoli Federico II, Napoli, Italy

  (antonio.montieri@unina.it)

- Danilo Giordano, PhD - Politecnico di Torino, Torino, Italy

  (danilo.giordano@polito.it)

- Claudio Fiandrino, PhD - IMDEA Networks Institute, Madrid, Spain

  (claudio.fiandrino@imdea.org)

- Jonatan Krolikowski, PhD - Huawei Technologies France SAS, Boulogne Billancourt, France
  (jonatan.krolikowski@huawei.com)

Important Dates:

----------------

- Submission Open Date: July 1, 2024

- Final Manuscript Submission Deadline: December 1, 2024

- Editorial Acceptance Deadline:    March 1, 2025

Manuscript Submission Information:

-----------------------------------

The journal's submission platform

(https://www.editorialmanager.com/comnet/default.aspx) is available for

receiving submissions to this Special Issue from July 1st, 2024. Authors are

advised to follow the Guide for Authors to prepare their manuscripts and select

the article type “VSI: GenXAI for Internet” when submitting online. More

information about the Special Issue, the Guide for Authors, and the submission

portal are available at the following link:

https://www.sciencedirect.com/journal/computer-networks/about/call-for-papers#generative-and-explainable-artificial-intelligence-for-internet-traffic-and-architectures

**********************************************************************

                      SPECIAL ISSUE DETAILS

**********************************************************************

In the realm of Internet traffic analysis, the advent of Artificial Intelligence

(AI) has marked a significant paradigm shift. With the proliferation of

Internet-connected devices and the exponential growth of traffic data,

traditional traffic analysis methods are struggling to cope with the sheer volume

and complexity of modern networks. Moreover, the dynamic nature of Internet

traffic patterns and the emergence of sophisticated cyber threats further

exacerbate the challenges faced by network operators and cybersecurity

professionals. In response, there is a pressing need for advanced analytical tools

that can provide accurate Internet traffic “visibility”, enable actionable insights

into traffic behavior, identify anomalies and intrusions, and ultimately enhance

network security and performance.

On the other hand, the collection, segmentation, and labeling of traffic datasets

are cumbersome processes, often requiring human experts to guide the different

stages. Additionally, factors like the dynamic nature of traffic, privacy concerns,

and the limited samples of certain traffic types (e.g., network attacks, IoT

devices) further challenge data collection. Moreover, while data-driven

techniques have the potential for outstanding performance and adaptability, they

often operate as black-box systems, making it difficult to understand their

behavior, improve their performance, or protect them from potential attacks.

This limits the interpretability and trust in these methods, affecting their

practical use.

The integration of generative and explainable AI techniques presents a promising

avenue for addressing these challenges. By harnessing the power of AI to generate

realistic traffic data and provide interpretable insights, researchers and

practitioners can overcome the limitations of traditional traffic analysis

methods. Generative AI models enable the creation of diverse and representative

traffic datasets, facilitating the training of AI-driven models for intrusion

detection and network optimization. Meanwhile, explainable AI techniques enhance

the transparency and trustworthiness of AI-driven traffic analysis, enabling

network operators to understand and interpret the decisions made by AI methods.

This special issue aims to delve into the methodological, technical, and

practical aspects of leveraging generative and explainable AI for Internet

traffic analysis and network architectures. By focusing on these cutting-edge

topics, we seek to provide a platform for researchers and practitioners to

explore innovative approaches, share insights, and advance state of the art.

The special issue will encompass a wide range of themes, including AI-driven

generation of standardized traffic datasets, network management aided by

generative AI, interpretable and trustworthy AI solutions for Internet traffic

analysis, and real-world applications of generative and explainable AI in

network optimization and security.

**********************************************************************