Safe AI

Special Session of the IEEE World Congress on Computational Intelligence (WCCI 2022), the International Joint Conference on Neural Networks (IJCNN 2022)

18 - 23rd July 2022, Padoua (Italy)

Dates

  • Abstract submission deadline: January 31, 2022 (11:59 pm AoE) strict deadline New submissions cannot be created past this deadline

  • Complete Papers submission deadline: February 14, 2022 (11:59 pm AoE) strict deadline

  • Decision notification: April 26, 2022

  • Camera ready paper due: May 23, 2022

  • Conference dates: July 18-23, 2022 (Padoua, Italy)

Description and Topics

The rise of Artificial Intelligence (AI) based system applications in multiple industrial sectors is mainly hampered by the lack of established dependability measures and methods to establish trust in the decisions taken autonomously. This special session focuses on establishing trust in such a dependable AI-based system for the application of autonomous vehicles.

Therefore, the special session targets advancing a wide range of enabling methods and technologies to ensure dependability features (such as functional safety, security, reliability, etc.) of AI-based systems for autonomous vehicles.

The aim is to cross-fertilize academic research with industrial research and development to explore options for application-oriented uptake of new technologies in the field of Safe AI approaches for autonomous vehicles. Autonomous vehicles in this context include automotive, avionics, robotics, and the industrial domain.

A list of relevant topics for this session includes, without being limited to, the following:

  • Application of AI for cyber-security

  • Application of AI for safety-critical applications

  • Safety/security co-engineering and risk assessment of autonomous & AI-based vehicles

  • Autonomous vehicles applications in automotive, robotic, industrial, and avionics domain

  • Dependable DevOps approaches for AI-based systems

  • Distributed AI-based systems engineering

  • Establishing metrics for evaluating dependability and safety of AI-based systems

  • Runtime verification methods for dependability features of AI-based systems

  • Methodologies for testing, verification, and validation of AI-based systems

  • Continual Learning under dependability constraints

  • Stability bounds (e.g., Lipschitz continuity bounds) on Neural Networks activations

  • Dependability assessment in dynamical AI models, e.g. Recurrent Neural Networks

  • Robust learning with out-of-distribution data and drifts

Submission

Papers submission for this Special Session follows the same process as for the regular sessions of WCCI 2022 (see https://wcci2022.org/submission/), which uses Microsoft CMT.

Submit your paper at the following link: https://cmt3.research.microsoft.com/IEEEWCCI2022/

1) In the Author Console, click on Create Submission
2) In the drop-down menu, choose "IJCNN"
3) In the Subject Areas section, please indicate "IJCNN-SS-22 Safe AI" as primary area.

Each paper should have 6 to MAXIMUM 8 pages, including figures, tables and references.

Important note: the review process for WCCI/IJCNN 2022 will be double-blind. For prospected authors, it is therefore mandatory to anonymize their manuscripts.

Organizers

Georg Macher (Graz University of Technology, Austria)

Claudio Gallicchio (University of Pisa, Italy)