Sequencing the Neurome: Towards Scalable Exact Parameter Reconstruction of Black-Box Neural Networks

ICLR 2026 Conference Submission21753 Authors

Keywords: Deep neural networks, Interpretability, Weight Recovery, Reverse Engineering

TL;DR: We present a new, state of the art algorithm for exact recovery of neural network weights

Abstract: Inferring the exact parameters of a neural network with only query access is an NP-Hard problem, with few practical existing algorithms. Solutions would have major implications for security, verification, interpretability, and understanding biological networks. The key challenges are the massive parameter space, and complex non-linear relationships between neurons. We resolve these challenges using two insights. First, we observe that almost all networks used in practice are produced by random initialization and first order optimization, an inductive bias that drastically reduces the practical parameter space. Second, we present a novel query generation algorithm that produces maximally informative samples, letting us untangle the non-linear relationships efficiently. We demonstrate reconstruction of a hidden network containing over 1.5 million parameters, and of one 7 layers deep, the largest and deepest reconstructions to date, with max parameter difference less than 0.0001, and illustrate robustness and scalability across a variety of architectures, datasets, and training procedures.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 21753