Challenges of Trustworthy Federated Learning: What's Done, Current Trends and Remaining Work
2025/07/21 by Rodríguez-Barroso, Nuria, García-Márquez, Mario, Luzón, M. Victoria +1 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2507.15796
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.
Citations
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
- Federated Learning for Cyber Physical Systems: A Comprehensive Survey
- Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter
- Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
- Unlearning Clients, Features and Samples in Vertical Federated Learning
- Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
- Trustworthy Federated Learning: Privacy, Security, and Beyond
- Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
- FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
- TDML -- A Trustworthy Distributed Machine Learning Framework
- Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges
- Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation
- Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
- Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
- Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey
- An Interpretable Client Decision Tree Aggregation process for Federated Learning
- Trust in AI: Progress, Challenges, and Future Directions
- Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance
- Federated Causality Learning with Explainable Adaptive Optimization
- Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark
- A Comprehensive Survey On Client Selections in Federated Learning
- Towards Personalized Federated Learning via Heterogeneous Model Reassembly
- When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection
- Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity
- Efficient Personalized Federated Learning via Sparse Model-Adaptation
- Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation
- Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
- A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacy
- Client Selection in Federated Learning: Principles, Challenges, and Opportunities
- Federated Unlearning for On-Device Recommendation
- Reward Systems for Trustworthy Medical Federated Learning
- Differentially Private Federated Learning on Heterogeneous Data
- Generalized Out-of-Distribution Detection: A Survey
- Generalized Out-of-Distribution Detection: A Survey
- Trustworthy AI: From Principles to Practices
- Trustworthy AI: From Principles to Practices
- Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
- A survey of human-in-the-loop for machine learning
- Federated Causal Inference in Heterogeneous Observational Data
- Sparse Personalized Federated Learning
- Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning
- Bayesian Variational Federated Learning and Unlearning in Decentralized Networks
- Learning Accurate and Interpretable Decision Rule Sets from Neural Networks
- Federated Learning for 6G: Applications, Challenges, and Opportunities
- To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devices
- Stochastic Client Selection for Federated Learning with Volatile Clients
- A Federated Learning Approach to Anomaly Detection in Smart Buildings
- Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
- Ensemble Distillation for Robust Model Fusion in Federated Learning
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Out-of-Distribution Generalization via Risk Extrapolation (REx)
- Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art
- TiFL: A Tier-based Federated Learning System
- Robust Aggregation for Federated Learning
- Proof of Federated Learning: A Novel Energy-recycling Consensus Algorithm
- Advances and Open Problems in Federated Learning
- Machine Unlearning
- Energy Efficient Federated Learning Over Wireless Communication Networks
- Provenance Data in the Machine Learning Lifecycle in Computational Science and Engineering
- Federated Learning: Challenges, Methods, and Future Directions
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
- Deep Leakage from Gradients
- Fair Resource Allocation in Federated Learning
- Robust and Communication-Efficient Federated Learning from Non-IID Data
- Federated Optimization in Heterogeneous Networks
- Analyzing Federated Learning through an Adversarial Lens
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Cited by
Related