pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data

A novel framework called FedNCA-ML has been proposed to enhance Federated Learning (FL) in multi-label scenarios, specifically addressing the challenges posed by label-distribution skew. This framework aligns feature distributions across clients and learns well-clustered representations inspired by Neural Collapse theory, which is crucial for applications like medical imaging where data privacy and heterogeneous distributions are significant concerns.

A novel generative AI-powered plugin has been proposed to enhance federated learning in heterogeneous IoT networks, addressing the challenges posed by Non-IID data distributions that hinder model convergence. This approach utilizes generative AI for data augmentation and a balanced sampling strategy to synthesize additional data for underrepresented classes, thereby improving the robustness and performance of the global model.

A recent perspective paper highlights the vulnerabilities of Federated Learning (FL) in military applications, particularly concerning Large Language Models (LLMs). It identifies prompt injection attacks as a significant threat that could compromise operational security and trust among allies. The paper outlines four key vulnerabilities: secret data leakage, free-rider exploitation, system disruption, and misinformation spread.

Hi-SAFE, a new framework for Hierarchical Secure Aggregation in Federated Learning (FL), addresses privacy and communication efficiency challenges in resource-constrained environments like IoT and edge networks. It enhances the security of sign-based methods, such as SIGNSGD-MV, by utilizing efficient majority vote polynomials derived from Fermat's Little Theorem.

A new decentralized peer-to-peer framework for federated learning (FL) has been proposed, challenging the traditional centralized star topology that limits personalization and robustness. This innovative approach allows clients to aggregate personalized updates from trusted peers, enhancing model training while maintaining data privacy.

The introduction of FIRM (Federated In-client Regularized Multi-objective alignment) presents a novel approach to aligning Large Language Models (LLMs) with human values by addressing the challenges of computational intensity and data privacy in training. This algorithm enhances communication efficiency and mitigates client disagreement drift, making it a significant advancement in Federated Learning (FL) methodologies.