Machine learning techniques are becoming increasingly popular in the field of networking. It offers promising solutions for network optimization, security, and management. However, the lack of transparency and interpretability in machine learning models poses challenges for understanding and trusting their decisions in critical networking scenarios. Moreover, ensuring safety and reliability is of utmost importance when deploying machine learning in real-world network environments.

Control and decision-making algorithms are critical for the operation of networks, hence we believe that the solutions should be safety bounded and interpretable. Understanding the decisions and behaviors of machine learning models is crucial for optimizing network performance, enhancing security, and ensuring reliable network operations. This is a very crucial topic which needs to be addressed, as network operators, managers or administrators are reluctant to use ML in production networks because of their critical and sensitive nature, e.g., as outages and performance degradations can be very costly.

We invite original research contributions as well as position papers addressing, but not limited to, the following topics:

Topics

• Explainable machine learning models for network performance optimization
• Interpretable anomaly detection and intrusion detection in networking systems
• Safety considerations and techniques for robust and reliable machine learning in networking
• Fairness, accountability, and transparency in machine learning for networking
• Hybrid models which combine formal methods and AI for explainability
• Explainable reinforcement learning for networking
• Explainable deep reinforcement learning for networking
• Safety bounded reinforcement learning for networking
• Explainable Graph neural networks for networking
• Explainable sequential decision-making
• Constraints-based explanations for networking
• Visualizations and tools for understanding and interpreting machine learning models in networking
• Case studies and real-world applications of explainable and safety bounded machine learning in networking
• Evaluation methods for explainable machine learning
• Fidelity of explainable machine learning methods

Submission procedure

Papers should be submitted via conext23-safe.hotcrp.com submission System.

All submitted papers will be assessed through a double-blind review process. This means that the authors do not see who are the reviewers and the reviewers do not see who are the authors.

As an author, please ensure that your paper submission does not directly or indirectly reveal the authors’ identities. Please find the requirements for a double-blind submission:

• Remove all personal information about the authors from the paper (e.g., names, affiliations).

• Remove acknowledgements to organizations and/or people.

• Referring to your previous work should be done similarly to any other work, as if your are not an author of that work.

• Do not add references to external repositories or technical reports that can be used to identify any of the authors or institutions/organization.

• Uploading a version of the paper to a non-peer-reviewed location (e.g., ArXiv) is acceptable. However, authors need to avoid advertising the paper on popular mailing list and social media until after the review process closes.

Submissions should be 6 pages maximum, plus one page for references, in 2-column 10pt ACM format. When using Latex, please download the style and templates from here.

Uncompress the zip file and look for sample-sigconf.tex in the /sample subdirectory. The file can be used as a starting point, or the confiation can be copied to your own file if one exists. In any case, your text file should use the following class

\documentclass[10pt,sigconf,letterpaper,anonymous,nonacm]{acmart} We encourage authors to share code/data at either submission time or at the camera ready.

All submitted papers will undergo a rigorous peer-review process by the program committee.

Please note that at least one author of each accepted submission should attend the workshop. All workshop participants must pay the appropriate registration fee. The registration of at least one author is required for the paper to be included in the conference proceedings.