# Vulnerability of Deep Learning

arXiv: https://arxiv.org/abs/1803.06111 · HTML: https://mlsanity.com/paper/1803.06111/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2018.

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

- [Eight challenges in developing theory of intelligence](https://mlsanity.com/paper/2306.11232/) (2023)
- [An Uncertainty-Informed Framework for Trustworthy Fault Diagnosis in Safety-Critical Applications](https://mlsanity.com/paper/2111.00874/) (2021)

## Abstract (arXiv)

The Renormalisation Group (RG) provides a framework in which it is possible to assess whether a deep-learning network is sensitive to small changes in the input data and hence prone to error, or susceptible to adversarial attack. Distinct classification outputs are associated with different RG fixed points and sensitivity to small changes in the input data is due to the presence of relevant operators at a fixed point. A numerical scheme, based on Monte Carlo RG ideas, is proposed for identifying the existence of relevant operators and the corresponding directions of greatest sensitivity in the input data. Thus, a trained deep-learning network may be tested for its robustness and, if it is vulnerable to attack, dangerous perturbations of the input data identified.