2024 CEC Special Session

In the big-data era, privacy becomes more and more important. When EC meets privacy computing, what will happen?

Introduction

In recent years, the rapid development of novel communication and distributed computing paradigms, such as cloud/edge computing, outsourcing computing, secure computing, and the Internet of Things (IoT), have brought new opportunities as well as new challenges to evolutionary computation (EC) methods. On the one hand, these new computing models can support distributed data perception, collection, learning, and optimization, promoting emerging research branches such as crowdsourcing, federated learning, and distributed data-driven optimization. EC has great potential in solving these distributed learning and optimization problems. On the other hand, the emerging computing paradigms also pose unprecedented privacy concerns for the EC frameworks, algorithms, and methods, rendered users severely vulnerable to privacy leakage, security attack, and fair decision. Hence, it is high time to investigate the privacy-preserving EC to cater for the era of cloud/edge computing, outsourcing computing, and federated computing

This special session aims to bring together researchers, practitioners and developers from different background areas such as artificial intelligence, computational intelligence, data privacy, secure computing, cloud/edge computing, and crowdsourcing to discuss the latest experience, research ideas and synergic research and development on fundamental issues and applications about challenges including privacy, security, and fairness issues in EC.

Scope

The topics of this special session include but are not limited to the following topics:

Formulation of privacy, security, and fairness in evolutionary computation
New opportunities, challenges, and modeling brought by secure computing, outsourcing computing, federated computing to evolutionary computation
Privacy-preserving, secure, or fairness-aware distributed optimization/learning/computing
Privacy-preserving, secure, or fairness-aware solutions for federated data-driven optimization/learning/computing
Secure computing powered privacy-preserving evolutionary computation
Evolutionary computation as a service
Privacy-preserving optimization paradigms for optimization, such as centralized optimization, distributed optimization, and surrogate-assistant optimization
Privacy-preserving and fairness-aware multi-objective optimization
Applications of privacy-preserving, secure, or fairness-aware framework, algorithms, and methods of evolutionary computation
Benchmarks/performance metrics for privacy-preserving, secure, or fairness-aware evolutionary computation