Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection

2025-10-10

AI Summary

The selection of privacy-preserving machine learning (PPML) frameworks lacks systematic, decision-support methodologies. Method: This paper proposes a multi-objective optimization–based automated recommendation approach. It formulates the deployment scenario as a constrained integer linear programming (ILP) problem, jointly optimizing computational efficiency, communication overhead, security strength, and scalability. By integrating multi-attribute decision analysis with PPML framework performance modeling, the method uniformly supports major paradigms—including secure multi-party computation (MPC), federated learning, and homomorphic encryption. Contribution/Results: To our knowledge, this is the first work to formalize PPML framework configuration as a tractable ILP model and realize end-to-end, user requirement–driven joint recommendation of framework selection and parameter configuration. Experiments across multiple real-world use cases demonstrate that the method consistently identifies optimal, constraint-satisfying configurations, significantly improving both selection efficiency and solution suitability.

Technology Category

• Machine Learning: Privacy
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Security and privacy of machine learning and AI applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Machine learning has become a crucial part of our lives, with applications spanning nearly every aspect of our daily activities. However, using personal information in machine learning applications has sparked significant security and privacy concerns about user data. To address these challenges, different privacy-preserving machine learning (PPML) frameworks have been developed to protect sensitive information in machine learning applications. These frameworks generally attempt to balance design trade-offs such as computational efficiency, communication overhead, security guarantees, and scalability. Despite the advancements, selecting the optimal framework and parameters for specific deployment scenarios remains a complex and critical challenge for privacy and security application developers. We present Prismo, an open-source recommendation system designed to aid in selecting optimal parameters and frameworks for different PPML application scenarios. Prismo enables users to explore a comprehensive space of PPML frameworks through various properties based on user-defined objectives. It supports automated filtering of suitable candidate frameworks by considering parameters such as the number of parties in multi-party computation or federated learning and computation cost constraints in homomorphic encryption. Prismo models every use case into a Linear Integer Programming optimization problem, ensuring tailored solutions are recommended for each scenario. We evaluate Prismo's effectiveness through multiple use cases, demonstrating its ability to deliver best-fit solutions in different deployment scenarios.

Problem

• Selecting optimal privacy-preserving ML frameworks for specific scenarios
• Balancing trade-offs between computational efficiency and security guarantees
• Automating framework selection through Linear Integer Programming optimization

Innovation

• Recommends optimal PPML frameworks via user-defined objectives
• Automates framework filtering using multi-party computation parameters
• Models use cases as Linear Integer Programming optimization problems