Secure Multi Party Computation

Secure Multi-Party Computation (MPC) enables multiple parties to jointly compute a function over their private inputs without revealing anything beyond the output. Current research focuses on applying MPC to enhance the privacy of machine learning models, particularly large language models and neural networks, often employing techniques like secret sharing and optimized cryptographic protocols to mitigate computational and communication overheads. This is crucial for protecting sensitive data in various applications, such as healthcare, finance, and collaborative research, while enabling the development and deployment of powerful machine learning models.