BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

2025-01-24

AI Summary

To address the dual challenges of substantial inter-subject variability in neural activity and the privacy sensitivity of fMRI data in cross-subject image reconstruction, this paper proposes a privacy-preserving federated collaborative decoding framework. Methodologically, it introduces a global-local cooperative architecture with a hybrid synchronization strategy, enabling fMRI feature alignment and cross-subject representation learning without sharing raw brain data—thereby jointly modeling population-level commonalities and subject-specific characteristics. A dynamic parameter synchronization mechanism is further incorporated to enhance federated training efficiency. Experimental results demonstrate state-of-the-art (SOTA) performance on both high-level (semantic) and low-level (pixel-wise) evaluation metrics, significantly improving multi-subject image reconstruction accuracy. This work is the first to empirically validate the feasibility of simultaneously optimizing privacy preservation and decoding performance in neuroimaging-based generative modeling.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Reconstructing perceived images from human brain activity forms a crucial link between human and machine learning through Brain-Computer Interfaces. Early methods primarily focused on training separate models for each individual to account for individual variability in brain activity, overlooking valuable cross-subject commonalities. Recent advancements have explored multisubject methods, but these approaches face significant challenges, particularly in data privacy and effectively managing individual variability. To overcome these challenges, we introduce BrainGuard, a privacy-preserving collaborative training framework designed to enhance image reconstruction from multisubject fMRI data while safeguarding individual privacy. BrainGuard employs a collaborative global-local architecture where individual models are trained on each subject's local data and operate in conjunction with a shared global model that captures and leverages cross-subject patterns. This architecture eliminates the need to aggregate fMRI data across subjects, thereby ensuring privacy preservation. To tackle the complexity of fMRI data, BrainGuard integrates a hybrid synchronization strategy, enabling individual models to dynamically incorporate parameters from the global model. By establishing a secure and collaborative training environment, BrainGuard not only protects sensitive brain data but also improves the image reconstructions accuracy. Extensive experiments demonstrate that BrainGuard sets a new benchmark in both high-level and low-level metrics, advancing the state-of-the-art in brain decoding through its innovative design.

Problem

• Brain-Computer Interface
• Privacy Protection
• Inter-Individual Variability

Innovation

• BrainGuard
• Privacy-Preserving
• Collaborative Learning