dsperse is a distributed Zero-Knowledge Machine Learning (zkML) toolkit that decomposes ONNX neural network models into circuit-compatible segments for verifiable AI inference. The core Rust library provides model slicing, circuit compilation (using JSTprove backend), witness generation, and proof verification. It exposes both a CLI interface and Python bindings via PyO3/Maturin for integration into ML pipelines. The architecture follows a clear separation: the slicer module handles ONNX graph decomposition and tiling strategies (channel split, dimension split, spatial tiling), the pipeline orchestrates execution with memory-efficient tensor caching, and the backend trait enables pluggable ZK proving systems. Content-addressed storage with SHA256 hashing ensures artifact integrity across distributed execution. Notable constraints: the license explicitly restricts operational use without written permission from the IP owner, and the codebase relies on nightly Rust toolchain with specific git dependencies (tract-onnx, jstprove_circuits) that create version coupling risks. Security advisories are partially ignored in the audit configuration.

JSTprove is a production-grade zero-knowledge proof system for verifying ONNX neural network inference. It compiles ML models into arithmetic circuits using the Expander Compiler Collection (ECC) frontend, generates witnesses, and produces proofs via a GKR/sumcheck-based prover with multiple polynomial commitment schemes (KZG, Hyrax, Orion, Basefold, WHIR). The system supports multiple efficient field arithmetics (Mersenne31, BabyBear, Goldilocks, BN254, GF2) with SIMD/AVX/NEON optimizations, and provides hardware acceleration through Metal and CUDA backends. The codebase is organized as a Rust workspace with ~30 crates, offering a CLI (`jstprove`, `jstprove-remainder`), Python bindings via PyO3, and a zkVM guest (Jolt). It is actively maintained by Inference Labs with regular commits, CI/CD pipelines, and e2e tests covering full model pipelines (LeNet, CIFAR CNN, MiniResNet). While primarily an application toolkit, it contains deep cryptographic research contributions in the form of advanced polynomial commitment constructions (sparse WHIR, hyper-bivariate KZG) and circuit optimizations (cross-layer GKR, LogUp range checks). Some hints (e.g., sigmoid, gridsample) carry documented soundness caveats, and the system relies on nightly Rust and platform-specific intrinsics, which may limit portability.