ACM/IEEE SEC 2026

FederatedEdge 2026: The 1st Workshop on Trustworthy Edge Intelligence for Federated Learning and Unlearning in Distributed Systems

The workshop will be co-located with ACM/IEEE SEC 2026 in Santa Clara, CA, USA. It is planned as a half-day workshop.

Call for Papers

Edge computing has become central to real-time data processing across IoT, healthcare, autonomous systems, and cyber-physical environments. Centralized machine learning approaches are increasingly unsuitable for these settings due to privacy constraints, communication overhead, and latency requirements. Federated learning addresses these challenges by enabling collaborative model training across distributed edge devices without sharing raw data. Yet modern applications also require the ability to remove previously learned information to comply with evolving data regulations and dynamic system requirements, a need that federated unlearning is emerging to address.

Despite significant advances, deploying federated learning and unlearning in real-world edge systems presents substantial challenges including system heterogeneity, limited computational resources, unreliable communication, and security vulnerabilities. This workshop brings together researchers and practitioners to discuss recent advances, system challenges, and real-world deployments of federated learning and unlearning at the edge, with the goal of fostering interdisciplinary collaboration and defining future research directions for scalable and trustworthy edge intelligence.

Topics of Interest

Core Themes

Edge intelligence and distributed AI systems
Federated learning in edge and IoT environments
Federated unlearning: theory, algorithms, and systems
Edge-cloud collaborative learning architectures

Systems and Optimization

Communication-efficient federated learning
Resource-aware and energy-efficient edge AI
Scheduling and scalability in distributed edge systems
Model compression and lightweight architectures
Handling system and data heterogeneity

Security, Privacy, and Trust

Privacy-preserving techniques such as differential privacy and secure aggregation
Trustworthy and explainable edge AI
Robustness against adversarial attacks
Secure and verifiable federated unlearning

Applications and Emerging Directions

Smart healthcare, wearable systems, and physiological signal analysis
Autonomous systems and intelligent transportation
Smart cities and IoT ecosystems
Industrial IoT and cyber-physical systems
Continual and lifelong learning at the edge
Multi-modal distributed learning
Sustainable and green edge AI
Edge AI integration with next-generation networks

Submission Guidelines

Only electronic submissions in PDF will be accepted.
Submitted papers must be written in English and rendered without error using standard PDF viewing tools.
Papers must be no longer than 6 single-spaced 8.5" x 11" pages, including figures and tables but excluding references, using 10-point type on 12-point leading, two-column format, Times Roman or similar font, within a text block 7.14" wide x 9.22" deep.
Pages must be numbered, and figures and tables must be legible in black and white.
Papers not meeting these criteria will be rejected without review.
At least one author for each accepted paper must register for the workshop.
Submissions should present original, unpublished work and must not be under review elsewhere.
All submissions will undergo peer review.
Accepted papers will be included in the workshop proceedings.
IEEE templates: https://www.ieee.org/conferences/publishing/templates.html
Submission website: TBD

Important Dates

Submission deadline: June 25, 2026

Acceptance notification: August 15, 2026

Camera-ready deadline: August 22, 2026

Workshop date: October 16, 2026

Workshop Organizers

Haitham Y. Adarbah, Texas A&M University-Kingsville, USA