Secure, Fair, and Privacy-Preserving Optimization and Learning
This special session focuses on optimization and learning in trustworthy distributed and federated environments, addressing security, privacy, and fairness requirements alongside performance.
Official links:
Call for Papers
Modern applications using computational intelligence increasingly operate in distributed environments where data is scattered across devices and organizations. While this paradigm enables scale and diversity, it introduces critical challenges in security, privacy protection, and fairness.
We welcome theoretical advances, algorithmic innovations, practical implementations, benchmarks, and real applications that jointly consider performance, robustness, privacy, and fairness in collaborative optimization and learning.
Important Dates
- Paper submission deadline: 31 January 2026 (23:59, Anywhere on Earth)
- Notification of acceptance: 15 March 2026
- Camera-ready submission: 15 April 2026
- Congress dates: 21–26 June 2026
Please always follow the official WCCI 2026 website for authoritative updates: WCCI 2026 website.
Submission
Authors are invited to submit original, unpublished research contributions that fall within the scope of this session. Submissions must follow the IEEE WCCI 2026 formatting and policies and will undergo the standard peer-review process.
To submit your paper, please visit the submission system: WCCI submission portal (Linklings), and select the special session "Secure, Fair, and Privacy-Preserving Optimization and Learning".
Topics of Interest
- Secure federated optimization and learning
- Fairness-aware federated optimization and learning
- Privacy-preserving Bayesian and distributed optimization
- Privacy-preserving evolutionary algorithms and data-driven optimization
- Byzantine-robust distributed optimization; adversarial robustness
- Fair and efficient resource allocation; privacy–utility–fairness trade-offs
- Metrics and benchmarks for trustworthy optimization and learning
- Multi-agent systems; graph-based federated learning; heterogeneity
Organizers
Contact
For inquiries about scope fit, collaboration, or submission details, please email any organizer: wangxilu@surrey.ac.uk, elluri@tamuct.edu, rmurthy@gapask.com.