Automated Data Protection
Status: Active (2021 - Present)
This project focuses on developing privacy-preserving machine learning techniques that allow organizations to analyze sensitive data while maintaining strict privacy guarantees. Our approach combines differential privacy, federated learning, and secure multi-party computation.
Research Goals
- Develop efficient privacy-preserving algorithms for machine learning
- Create frameworks for automated compliance with privacy regulations
- Design systems for secure multi-party computation in distributed environments
Team Members
Prof. Sarah Johnson (Lead), Dr. Michael Chen, Li Wei, Emily Parker
Funding
National Science Foundation (Grant #2035781)
Energy-Efficient Neural Networks
Status: Active (2022 - Present)
We're developing compact neural network architectures that deliver state-of-the-art performance while requiring significantly less computational resources. This research is crucial for deploying AI in resource-constrained environments like mobile devices and IoT systems.
Research Goals
- Design neural network architectures with reduced parameter counts
- Develop efficient training and inference algorithms
- Create benchmarks for energy efficiency in neural networks
Team Members
Funding
Department of Energy (Grant #DOE-AI-2022-104)
Advanced Computer Vision Systems
Status: Active (2020 - Present)
This project explores novel computer vision approaches for 3D scene understanding, object recognition, and tracking in complex environments. We're developing algorithms that can operate in challenging conditions like poor lighting, occlusion, and motion blur.
Research Goals
- Develop robust 3D object recognition algorithms
- Create methods for scene understanding in dynamic environments
- Design efficient tracking systems for multiple moving objects
Team Members
Prof. James Wong (Lead), Dr. Sophia Martinez, Robert Johnson
Funding
DARPA (Contract #CV-2020-789)
