CryptOracle: A Modular Framework to Characterize Fully Homomorphic Encryption

2025-10-03

AI Summary

Fully homomorphic encryption (FHE) suffers from prohibitive computational overhead—up to six orders of magnitude slower than plaintext execution—severely hindering its practical deployment in privacy-preserving machine learning. Method: Addressing performance bottlenecks of the CKKS scheme in OpenFHE, we propose CryptOracle, the first modular evaluation framework supporting multi-abstraction-level, cross-platform (Intel/AMD) microarchitectural event collection and energy modeling. It integrates a three-tiered benchmark suite—workload-, microbenchmark-, and primitive-level—combined with hardware performance counters and empirical power measurements. Contribution/Results: CryptOracle builds error-bounded predictive models achieving ±7.02% runtime and ±9.74% energy estimation accuracy. Its extensible architecture enables co-optimization across algorithms, software, and hardware layers, providing a unified, open-source platform for system-level FHE evaluation and optimization.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Security and Privacy: Applications of cryptography
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Privacy-preserving machine learning has become an important long-term pursuit in this era of artificial intelligence (AI). Fully Homomorphic Encryption (FHE) is a uniquely promising solution, offering provable privacy and security guarantees. Unfortunately, computational cost is impeding its mass adoption. Modern solutions are up to six orders of magnitude slower than plaintext execution. Understanding and reducing this overhead is essential to the advancement of FHE, particularly as the underlying algorithms evolve rapidly. This paper presents a detailed characterization of OpenFHE, a comprehensive open-source library for FHE, with a particular focus on the CKKS scheme due to its significant potential for AI and machine learning applications. We introduce CryptOracle, a modular evaluation framework comprising (1) a benchmark suite, (2) a hardware profiler, and (3) a predictive performance model. The benchmark suite encompasses OpenFHE kernels at three abstraction levels: workloads, microbenchmarks, and primitives. The profiler is compatible with standard and user-specified security parameters. CryptOracle monitors application performance, captures microarchitectural events, and logs power and energy usage for AMD and Intel systems. These metrics are consumed by a modeling engine to estimate runtime and energy efficiency across different configuration scenarios, with error geomean of $-7.02%sim8.40%$ for runtime and $-9.74%sim15.67%$ for energy. CryptOracle is open source, fully modular, and serves as a shared platform to facilitate the collaborative advancements of applications, algorithms, software, and hardware in FHE. The CryptOracle code can be accessed at https://github.com/UnaryLab/CryptOracle.

Problem

• Characterizing performance overhead in Fully Homomorphic Encryption implementations
• Reducing computational costs for privacy-preserving machine learning
• Developing modular framework to evaluate FHE across different configurations

Innovation

• Modular framework evaluates Fully Homomorphic Encryption performance
• Benchmark suite covers multiple abstraction levels and security parameters
• Predictive model estimates runtime and energy across configurations