🤖 AI Summary
Selecting appropriate zero-knowledge proof (ZKP) systems for privacy-preserving computation on resource-constrained edge devices remains challenging due to trade-offs in performance, security assumptions, and hardware compatibility.
Method: This work presents the first end-to-end empirical evaluation of zk-SNARKs (Groth16) and zk-STARKs on a commodity ARM64 platform, measuring proof generation/verification latency, proof size, CPU bottlenecks, and trust model requirements.
Contribution/Results: Groth16 achieves 68× faster proof generation and 123× smaller proofs than zk-STARK, but incurs slower verification and requires a trusted setup. Conversely, zk-STARK offers faster verification, post-quantum security, and no trusted setup—yet suffers from significantly higher generation cost and larger proofs. The study identifies critical impacts of low-level implementation choices and ARM64 microarchitectural features on real-world ZKP performance. It further proposes application-driven ZKP selection guidelines tailored for edge deployment, providing empirically grounded insights and practical recommendations for deploying privacy-enhancing technologies in constrained environments.
📝 Abstract
Zero-knowledge proofs (ZKPs) are central to secure and privacy-preserving computation, with zk-SNARKs and zk-STARKs emerging as leading frameworks offering distinct trade-offs in efficiency, scalability, and trust assumptions. While their theoretical foundations are well studied, practical performance under real-world conditions remains less understood.
In this work, we present a systematic, implementation-level comparison of zk-SNARKs (Groth16) and zk-STARKs using publicly available reference implementations on a consumer-grade ARM platform. Our empirical evaluation covers proof generation time, verification latency, proof size, and CPU profiling. Results show that zk-SNARKs generate proofs 68x faster with 123x smaller proof size, but verify slower and require trusted setup, whereas zk-STARKs, despite larger proofs and slower generation, verify faster and remain transparent and post-quantum secure. Profiling further identifies distinct computational bottlenecks across the two systems, underscoring how execution models and implementation details significantly affect real-world performance. These findings provide actionable insights for developers, protocol designers, and researchers in selecting and optimizing proof systems for applications such as privacy-preserving transactions, verifiable computation, and scalable rollups.