A Note on Non-Composability of Layerwise Approximate Verification for Neural Inference
Cryptography and Security
2026-02-18 v1 Machine Learning
Abstract
A natural and informal approach to verifiable (or zero-knowledge) ML inference over floating-point data is: ``prove that each layer was computed correctly up to tolerance ; therefore the final output is a reasonable inference result''. This short note gives a simple counterexample showing that this inference is false in general: for any neural network, we can construct a functionally equivalent network for which adversarially chosen approximation-magnitude errors in individual layer computations suffice to steer the final output arbitrarily (within a prescribed bounded range).
Cite
@article{arxiv.2602.15756,
title = {A Note on Non-Composability of Layerwise Approximate Verification for Neural Inference},
author = {Or Zamir},
journal= {arXiv preprint arXiv:2602.15756},
year = {2026}
}