Paper 2026/1063

The Cost of Intelligence: Proving Machine Learning Inference with Zero-Knowledge

Nick Cosby, Modulus Labs

Vishruti Ganesh, Modulus Labs

Ende Shen, Modulus Labs

Daniel Shorr, Modulus Labs

Benjamin Wilson, Modulus Labs

Abstract

Zero-Knowledge (ZK) scaling solutions have seen wide adoption recently in emerging technologies, such as cryptocurrencies. Yet, the concrete limits of current ZK proof systems are not well understood for an emerging class of particularly compute-heavy operations -- artificial intelligence algorithms. To that end, this technical whitepaper explores the current limits of constructing proofs for machine learning computation. We do this by benchmarking a common suite of multi-layer perceptrons (MLPs) across a set of zero-knowledge proof systems, including Groth16, Gemini, Winterfell, Halo2, Plonky2, and zkCNN. We showcase comparisons of proof time and memory consumption between the aforementioned proof systems, and how each scales with increasingly large and deep MLPs, examining bottlenecks for both proof time and memory consumption for each proof system. We conclude by examining the performance needed for production grade use-cases, motivating future work in a custom prover.

Note: Note: This paper was originally published on January 31st, 2023 at https://github.com/Modulus-Labs/Papers/blob/master/Cost_Of_Intelligence.pdf

@misc{cryptoeprint:2026/1063,
      author = {Ryan Cao and Nick Cosby and Vishruti Ganesh and Ende Shen and Daniel Shorr and Benjamin Wilson},
      title = {The Cost of Intelligence: Proving Machine Learning Inference with Zero-Knowledge},
      howpublished = {Cryptology {ePrint} Archive, Paper 2026/1063},
      year = {2026},
      url = {https://eprint.iacr.org/2026/1063}
}