2nd International Workshop on Artificial Intelligence for Autonomous computing Systems (AI4AS 2024)

Co-located with ACSOS 2024, which takes place in Aarhus (Denmark) - September 16-20, 2024.

Important Dates

  • Submission deadline: July 12th, 2024 (extended, firm)
  • Notification to authors: July 26th, 2024
  • Camera-ready deadline: August 2nd, 2024
  • Workshop: September 20th, 2024

All times in Anywhere on Earth (AoE) timezone.

Program

Room: Mortensenstuen

Schedule

9.00 - 9.05Opening
9.05 - 10.00Keynote: Stefano Iannucci (Roma Tre University, Italy), “From Attack Trees to Timed Stochastic Games: a Novel Intrusion Response Approach”
10.00 - 10.30Coffe Break
10.30 - 11.00Generative Models for Temporal-based Task Definition. Lukas Koch Vindbjerg (Aarhus University) and Lukas Esterle (Aarhus University)
11.00 - 11.30Meta-Adaptation Goals: Leveraging Feedback Loop Requirements for Effective Self-Adaptation. Raffaela Groner (Chalmers University of Technology), Ricardo Caldas (Chalmers University of Technology) and Rebekka Wohlrab (Chalmers University of Technology)
11.30 - 12.00Machine Learning to Predict Risk Management Applications Performance. Laura De Giorgi (Politecnico di Milano) and Danilo Ardagna (Politecnico di Milano)
12.00 - 13.00Lunch
13.00 - 13.30Principled Transfer Learning for Autonomic Systems: A Neuro-Symbolic Vision. Christian Medeiros Adriano (Hasso Plattner Institute), Sona Ghahremani (Hasso Plattner Institute) and Holger Giese (Hasso Plattner Institute)
13.30 - 14.00Safety-Aware Adaptive Reinforcement Learning for Mobile Assistive-Care Robots. Qi Zhang (University of York), Ioannis Stefanakos (University of York), Javier Camara (University of Málaga) and Radu Calinescu (University of York)
14.00 - 14.30Towards a Multi-Armed Bandit Approach for Adaptive Load Balancing in Function-as-a-Service Systems. Gabriele Russo Russo (University of Rome Tor Vergata), Enrico D’Alessandro (Tor Vergata University of Rome), Valeria Cardellini (Tor Vergata University of Rome) and Francesco Lo Presti (Tor Vergata University of Rome)
14.30 - 15.00Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems. Juan C. Rosero (Trinity College Dublin), Nicolás Cardozo (Universidad de los Andes) and Ivana Dusparic (Trinity College Dublin)

Keynote

From Attack Trees to Timed Stochastic Games: a Novel Intrusion Response Approach

Self-Protecting Systems (SPS) are envisioned as the next frontier in the runtime protection of computer systems, and are usually designed following a pipeline that combines at least two stages: Intrusion Detection and Intrusion Response. While the former has been investigated for decades, Intrusion Response is a relatively new field of research, which slowly gained interest in the past few years, in part due to the advances in the field of Artificial Intelligence. Most recent Intrusion Response Systems (IRSs) use models to characterize the attack patterns and the dynamics of the protected system. Such models are typically based on some mathematical framework, and thus require a low-level modeling activity that is often difficult and error prone, even to the experienced end-user. Furthermore, most of the model-based approaches proposed so far do not structurally include the notion of time, which is necessary to model non-instantaneous defense and attack actions. In this talk, we introduce a novel methodology for the automatic generation of IRSs based on Timed Competitive Stochastic Games from augmented Attack-Defense Trees (ADT), a formalism that is commonly used to represent attack patterns. We show that the resulting stochastic game always yields a reward that is at least as good as the reward obtainable with an augmented ADT and discuss the scalability of the proposed approach in terms of planning time and memory usage.

Speaker

Stefano Iannucci is an Assistant Professor of Computer Engineering at Roma Tre University and an Adjunct Professor of Computer Science and Engineering at Mississippi State University. He received his Ph.D. in 2015 from the University of Rome Tor Vergata. His research is in the broad area of autonomic computing and, more recently, Intrusion Response.

He published over 30 papers in top journals and conferences. Dr. Iannucci has chaired several international workshops and has been the workshops chair for IEEE ICCAC 2017 and ACM/SPEC ICPE 2023. He is Associate Editor of Springer Cluster Computing and part of the Review Board of IEEE Transactions on Parallel and Distributed Systems.

Call for Papers

Modern computing systems are large and heterogeneous. Their complexity is hardly manageable by a human being, especially when it comes to taking timely decisions in highly dynamic environments or to guarantee strict Quality-of-Service requirements. Not surprisingly, recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) significantly impacted and fostered the development of autonomous computing systems, providing new or enhanced methodologies to cope with system complexity and uncertainty. AI and ML techniques are increasingly adopted to assist or guide system self-adaptation, as they are used, e.g., to extract relevant information from highly dimensional and noisy monitoring data, to predict internal or external dynamics, to automatically plan adaptation actions.

However, there are still several challenges to face for researchers and practitioners aiming to take advantage of these methodologies and incorporate them in their systems. Fundamental issues towards the applicability of AI and ML techniques across diverse domains must be investigated, especially as regards the accuracy, robustness, explainability, safety, security, performance and sustainability of AI-driven autonomous computing systems.

In this workshop, we solicit high quality contributions that fit with the overarching theme of AI and ML meeting autonomous computing systems. We invite submissions of original research papers, as well as vision papers and experience reports.

Authors of selected papers from the workshop will be invited to submit an extended version of their work to the special issue of ACM Transactions on Autonomous and Adaptive Systems (TAAS) on “Artificial Intelligence for Adaptive and Autonomous Cloud/Edge Computing Systems”.

Topics

The aim of the workshop is to share new findings, exchange ideas and discuss research challenges on the following topics (not an exhaustive list):

  • AI and ML techniques for self-* computing systems
  • Architectures and frameworks for AI integration
  • Sustainability aspects of AI-driven adaptation
  • Federated and multi-agent learning approaches for decentralized adaptation
  • Robustness, explainability, safety, and security of AI-driven computing systems
  • Integration of large language models (LLMs) into autonomous computing systems
  • Self-adaptation for AI/ML systems
  • Case studies and real-world implementations of AI for autonomous computing systems

Organizers

Gabriele Russo Russo

Valeria Cardellini

Paolo Romano

Program Committee

Sherif Abdelwahed

Ivana Dusparic

David Garlan

Ann Gentile

Janick Edinger

Shashikant Ilager

Emilio Incerto

Matteo Nardelli

Luis Rodrigues

Gregor Schiele

Author Information

All submissions are required to be formatted according to the standard IEEE Computer Society Press proceedings style guide. Papers can be submitted in PDF format via EasyChair, making sure to select the track “International Workshop on Artificial Intelligence for Autonomous computing Systems”. Submitted manuscripts must be no longer than 6 pages (including figures, tables, and references).

Accepted papers will be published in the ACSOS Companion volume and will appear in IEEE Xplore.

As per the standard IEEE policies, all submissions should be original, i.e., they should not have been previously published in any conference proceedings, book, or journal and should not currently be under review for another archival conference. We would like to also highlight IEEE’s policies regarding plagiarism and self-plagiarism, available here.

Previous Editions