# Neural Networks, Inside Out: Solving for Inputs Given Parameters (A Preliminary Investigation)

arXiv: https://arxiv.org/abs/2110.03649 · HTML: https://mlsanity.com/paper/2110.03649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 2 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 1 of 1)

- [Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning](https://mlsanity.com/paper/2006.02894/) (2020)

## Abstract (arXiv)

Artificial neural network (ANN) is a supervised learning algorithm, where parameters are learned by several back-and-forth iterations of passing the inputs through the network, comparing the output with the expected labels, and correcting the parameters. Inspired by a recent work of Boer and Kramer (2020), we investigate a different problem: Suppose an observer can view how the ANN parameters evolve over many iterations, but the dataset is oblivious to him. For instance, this can be an adversary eavesdropping on a multi-party computation of an ANN parameters (where intermediate parameters are leaked). Can he form a system of equations, and solve it to recover the dataset?