zkSDK: Streamlining zero-knowledge proof development through automated trace-driven ZK-backend selection

TL;DR

zkSDK is a modular framework that simplifies zero-knowledge proof development by automatically selecting the most suitable ZK backend based on program profiling and user criteria, reducing complexity for developers.

Contribution

It introduces zkSDK with Presto, a novel profiling language, and a dynamic backend selection algorithm, enhancing ease of use and optimizing ZK proof generation.

Findings

Effective automatic backend selection for real-world workloads

Improved developer experience with seamless backend switching

Demonstrated performance benefits of optimal backend choice

Abstract

The rapid advancement of creating Zero-Knowledge (ZK) programs has led to the development of numerous tools designed to support developers. Popular options include being able to write in general-purpose programming languages like Rust from Risc Zero. Other languages exist like Circom, Lib-snark, and Cairo. However, developers entering the ZK space are faced with many different ZK backends to choose from, leading to a steep learning curve and a fragmented developer experience across different platforms. As a result, many developers tend to select a single ZK backend and remain tied to it. This thesis introduces zkSDK, a modular framework that streamlines ZK application development by abstracting the backend complexities. At the core of zkSDK is Presto, a custom Python-like programming language that enables the profiling and analysis of a program to assess its computational workload intensity. Combined with user-defined criteria, zkSDK employs a dynamic selection algorithm to automatically choose the optimal ZK-proving backend. Through an in-depth analysis and evaluation of real-world workloads, we demonstrate that zkSDK effectively selects the best-suited backend from a set of supported ZK backends, delivering a seamless and user-friendly development experience.