Challenges of Trustworthy Federated Learning: What's Done, Current Trends and Remaining Work

2025-07-21

AI Summary

Federated learning (FL) struggles to meet the holistic requirements of Trustworthy Artificial Intelligence (TAI)—encompassing privacy, ethics, and technical compliance—within distributed architectures, particularly in high-risk domains. Method: This paper pioneers a TAI-aligned framework to systematically identify and categorize three critical FL challenges: (i) privacy leakage risks, (ii) algorithmic bias and lack of explainability, and (iii) cross-jurisdictional legal compliance gaps. Leveraging a structured bidirectional mapping between TAI requirements and FL capabilities—grounded in IEEE, NIST, and EU AI Act standards—we conduct a comprehensive literature review to pinpoint coverage deficits in existing technical approaches. Contribution/Results: The analysis uncovers fundamental unresolved tensions, notably the tripartite trade-off among robustness, fairness, and auditability. We propose concrete research directions for trustworthy FL deployment, offering theoretical foundations and governance insights to enable safe adoption in high-stakes applications such as healthcare and finance.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• Responsible Web: Fairness, accountability, transparency and ethics of web technologies
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In recent years, the development of Trustworthy Artificial Intelligence (TAI) has emerged as a critical objective in the deployment of AI systems across sensitive and high-risk domains. TAI frameworks articulate a comprehensive set of ethical, legal, and technical requirements to ensure that AI technologies are aligned with human values, rights, and societal expectations. Among the various AI paradigms, Federated Learning (FL) presents a promising solution to pressing privacy concerns. However, aligning FL with the rest of the requirements of TAI presents a series of challenges, most of which arise from its inherently distributed nature. In this work, we adopt the requirements TAI as a guiding structure to systematically analyze the challenges of adapting FL to TAI. Specifically, we classify and examine the key obstacles to aligning FL with TAI, providing a detailed exploration of what has been done, the trends, and the remaining work within each of the identified challenges.

Problem

• Aligning Federated Learning with Trustworthy AI requirements
• Addressing privacy concerns in distributed AI systems
• Identifying challenges and trends in Trustworthy Federated Learning

Innovation

• Federated Learning for privacy preservation
• Systematic analysis of TAI alignment challenges
• Classification of obstacles in FL-TAI integration