# Incorrect by Construction: Fine Tuning Neural Networks for Guaranteed Performance on Finite Sets of Examples

arXiv: https://arxiv.org/abs/2008.01204 · HTML: https://mlsanity.com/paper/2008.01204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

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

- [Provably Safe Neural Network Controllers via Differential Dynamic Logic](https://mlsanity.com/paper/2402.10998/) (2024)
- [Automated Repair of Neural Networks](https://mlsanity.com/paper/2207.08157/) (2022)

## Abstract (arXiv)

There is great interest in using formal methods to guarantee the reliability of deep neural networks. However, these techniques may also be used to implant carefully selected input-output pairs. We present initial results on a novel technique for using SMT solvers to fine tune the weights of a ReLU neural network to guarantee outcomes on a finite set of particular examples. This procedure can be used to ensure performance on key examples, but it could also be used to insert difficult-to-find incorrect examples that trigger unexpected performance. We demonstrate this approach by fine tuning an MNIST network to incorrectly classify a particular image and discuss the potential for the approach to compromise reliability of freely-shared machine learning models.