# A Protection against the Extraction of Neural Network Models

arXiv: https://arxiv.org/abs/2005.12782 · HTML: https://mlsanity.com/paper/2005.12782/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2020.

## Built on by (most cited first, 2 of 2)

- [I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences](https://mlsanity.com/paper/2206.08451/) (2022)
- [Parameter identifiability of a deep feedforward ReLU neural network](https://mlsanity.com/paper/2112.12982/) (2021)

## Abstract (arXiv)

Given oracle access to a Neural Network (NN), it is possible to extract its underlying model. We here introduce a protection by adding parasitic layers which keep the underlying NN's predictions mostly unchanged while complexifying the task of reverse-engineering. Our countermeasure relies on approximating a noisy identity mapping with a Convolutional NN. We explain why the introduction of new parasitic layers complexifies the attacks. We report experiments regarding the performance and the accuracy of the protected NN.