Research Thrust

Secure & Privacy-Preserving Distributed Intelligence

Building machine learning and data-sharing systems that remain accurate and useful even when data, participants, or infrastructure cannot be fully trusted.

Modern intelligent systems rarely learn from a single, centralized dataset. Instead, they train and operate across distributed organizations, edge devices, sensor networks, and federated infrastructures where data ownership, privacy regulations, and adversarial participants all constrain what can be shared and how.

This thrust investigates methods for secure and privacy-preserving distributed intelligence, including:

Federated and distributed learning under non-IID data, communication constraints, and Byzantine or adversarial participants
Privacy-preserving computation techniques, including differential privacy, secure aggregation, and privacy-utility trade-off analysis
Trust and integrity mechanisms for multi-party and cross-organizational data pipelines
Resilient distributed architectures for scientific and mission-critical infrastructure

The goal is to enable organizations, scientific collaborations, and networked systems to collaboratively build and deploy intelligent models without compromising the confidentiality, integrity, or availability of the underlying data.

Related Work

Publications in this Area

Conference Submitted

Manuscript submitted — under peer review; not yet published.

FedTrace: Forensic Client Attribution and Attack-Onset Localization in Heterogeneous Federated Learning

Al Amin

NDSS 2027, 2027

AI Security, Cyber Defense & ForensicsSecure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin. "FedTrace: Forensic Client Attribution and Attack-Onset Localization in Heterogeneous Federated Learning." Submitted to NDSS 2027.

Journal Published

Grid-Wise Physics-Informed Federated Learning with Spatially-Localized Feature Regularization for Heterogeneous Medical Image Classification

Al Amin

IEEE Access, 2026

Secure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin. "Grid-Wise Physics-Informed Federated Learning with Spatially-Localized Feature Regularization for Heterogeneous Medical Image Classification." IEEE Access, 2026.

Conference Published

Lightweight Privacy-First Federated Learning for Medical AI

Al Amin, et al.

EAI SecureComm, 2026

Secure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin et al. "Lightweight Privacy-First Federated Learning for Medical AI." EAI SecureComm, 2026.

Conference Published

Privacy-Preserving Federated Vision Transformer Learning Leveraging Lightweight Homomorphic Encryption in Medical AI

Al Amin, et al.

IEEE ICNC, 2026

Secure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin et al. "Privacy-Preserving Federated Vision Transformer Learning Leveraging Lightweight Homomorphic Encryption in Medical AI." IEEE ICNC, 2026.

Conference Published

AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach

Al Amin, et al.

IEEE CCNC, 2025

Secure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin et al. "AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach." IEEE CCNC, 2025.

Conference Published

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification

Al Amin, et al.

IEEE CCNC, 2025

Secure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin et al. "ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification." IEEE CCNC, 2025.

Conference Published

Multi Hospital MRI Analysis with Privacy-Preserving Ensemble Enhanced Federated Learning

Al Amin, et al.

IEEE SoutheastCon, 2024

Secure & Privacy-Preserving Distributed Intelligence

Cite this work

Al Amin et al. "Multi Hospital MRI Analysis with Privacy-Preserving Ensemble Enhanced Federated Learning." IEEE SoutheastCon, 2024.

← Back to all research areas