SAFE-HE 2026

As AI systems become increasingly decentralized, the need for secure, privacy-aware training mechanisms is critical. Federated Learning enables collaborative model training across multiple parties without requiring the exchange of raw data, making it a promising approach for data-sensitive environments. At the same time, Homomorphic Encryption allows computations to be performed directly on encrypted data, ensuring end-to-end confidentiality.

SAFE-HE is designed to explore the intersection of these two technologies, addressing the growing demand for trustworthy AI by uniting researchers and practitioners from machine learning, cryptography, privacy, and HPC.

The objective of this workshop is to bring together researchers and practitioners to explore recent advances in integrating Federated Learning (FL) and Homomorphic Encryption (HE), with a focus on both theoretical foundations and practical implementations. The workshop aims to identify key open challenges and highlight promising research directions for secure and efficient distributed learning. A core goal is to foster interdisciplinary collaboration across the cryptography, machine learning, privacy, cybersecurity, and systems communities, promoting a shared understanding of the complex issues at the intersection of these fields. Additionally, the workshop will serve as a platform to disseminate tools, methodologies, and results developed under the CIBER-CAFE initiative, supporting the broader adoption and impact of secure collaborative learning technologies.

Topics of interest for the workshop include, but are not limited to, the following areas:

• • Algorithms, protocols, frameworks for FL using HE and other privacy techniques.

  • Fairness, robustness, and trust in decentralized learning.

  • Deployment and optimization across platforms, from edge to HPC.

  • Benchmarks, datasets, tools for reproducible, efficient secure FL workflows.

  • Socio-technical and regulatory aspects including post-quantum security and compliance.

• Antonio J. Peña, Barcelona Supercomputing Center, Spain
  Keynote: "Deep learning and homomorphic encryption: Where are we?"

TBD

• Paper submission deadline: 8 November 2025 (AoE)

• Notification of acceptance:  30 November 2025

• Manuel F. Dolz, Universitat Jaume I, Spain, dolzm@uji.es

• Sandra Catalán, Universitat Jaume I, Spain, catalans@uji.es

• Larbi Boubchir, University of Paris 8, France

• Darwin Quezada Gaibor, Universitat Jaume I, Spain

• Damien Ligier, DESILO, Seoul, South Korea

• Christian Prehofer, Technical University of Munich, Germany

• Luis Bernardo Pulido Gaytan, National College of Ireland, Ireland

• Leonel Sousa, INESC-ID/IST, Universidade de Lisboa, Portugal

Authors submitting papers for SAFE-HE 2026 must do so via the EasyChair submission web page for SAFE-HE 2026. Authors are invited to submit technical papers of no more than 12 pages in PDF format, including figures and references.

Submitted papers must contain original work that has not appeared in, and is not under consideration for, another conference, journal, or workshop. The review process is double-blind.

Format: single-column, maximum 12 pages including figures and references, following the ACM Proceedings Style.

Templates:

• Word (docx): https://www.acm.org/binaries/content/assets/publications/taps/acm_submission_template.docx

• LaTeX (zip): https://portalparts.acm.org/hippo/latex_templates/acmart-primary.zip

• Overleaf (ACM LaTeX Template): https://www.overleaf.com/gallery/tagged/acm-official

Submission link: https://easychair.org/my/conference?conf=safehe2026

Accepted papers will be published together with SCA/HPC Asia 2026 proceedings.

Information about registration at SCA/HPC Asia 2026 website.