Privacy-first ear biometric segmentation - 99%+ accuracy with <2M parameters for edge authentication and GDPR compliance

A stateful AI agent framework powered by the Cognitive Lattice to solve complex tasks with persistent memory and reliable tool orchestration.

A curated collection of privacy-preserving machine learning techniques, tools, and practical evaluations. Focuses on differential privacy, federated learning, secure computation, and synthetic data generation for implementing privacy in ML workflows.

Production Android AI with ExecuTorch 1.0 - Deploy PyTorch models to mobile with NPU acceleration and 50KB footprint

Privacy-first decentralized AI training network combining federated learning, blockchain incentives, and quantum-safe cryptography. Enable secure collaborative model development without sharing raw data.

Federated training on MNIST with differential privacy noise + FL metrics tracking

Build a decentralized AI infrastructure on Solana, enabling secure on-chain model training and creating a global marketplace for AI inference services.

Privacy-preserving AI for global agriculture. Enables policy-gated federated learning for sustainable yields and climate resilience while maintaining full farmer data sovereignty.

Privacy-preserving healthcare AI for global oncology research. Features policy-gated federated learning, HIPAA/GDPR compliance evidence, and a comprehensive research dashboard.

Policy-gated federated learning for global climate intelligence. Enables nation-sovereign AI for carbon tracking and risk analytics without sharing raw environmental data.

Flutter app: on-device MedGemma, FHIR via MCP, Apple Health + SQLite for private health Q&A and research.

Agentic digital health assistant, powered by Federated Learning, autonomously supports patient recovery post-discharge while preserving privacy across clinical institutions.

Policy-gated federated learning for global supply-chain intelligence. Enables enterprise-sovereign AI for disruption prediction and carbon-compliant routing without sharing raw logistics data.

A decentralized, diffusion-based U-Net framework for privacy-preserving brain tumor segmentation from MRI images.

A Modular Knowledge Transfer System for Large Language Models

Implementation of Federated Unlearning for medical image classification using the FedEraser approach. Demonstrates how client data contributions can be removed from a trained federated learning model without full retraining.

Privacy-preserving medical diagnosis system using Federated Learning (Flower), Differential Privacy (Opacus), and FastAPI.

A federated healthcare triage assistant that routes patients to appropriate care while ensuring privacy and reducing health disparities via multi-stakeholder governance.

A stateless, human-inspired memory architecture that replaces verbatim logs with meaning-level abstraction — enabling O(1) inference, zero-knowledge privacy, and the next-generation Intent Engine.

Federated Unlearning framework for medical imaging using FedEraser, enabling efficient removal of client-specific data from trained models without full retraining.