# An Estimator for the Sensitivity to Perturbations of Deep Neural Networks

Source: [An Estimator for the Sensitivity to Perturbations of Deep Neural Networks](<https://www.sota2.com/research/paper/68fa5aaf1e209131ce9c1e9e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T16:38:49.818Z

Authors: Naman Maheshwari, Nicholas Malaya, Scott Moe, Jaydeep P. Kulkarni, Sudhanva Gurumurthi

Published: 2023-07-24T10:33:32.000Z

## Abstract

For Deep Neural Networks (DNNs) to become useful in safety-critical applications, such as self-driving cars and disease diagnosis, they must be stable to perturbations in input and model parameters. Characterizing the sensitivity of a DNN to perturbations is necessary to determine minimal bit-width precision that may be used to safely represent the network. However, no general result exists that is capable of predicting the sensitivity of a given DNN to round-off error, noise, or other perturbations in input. This paper derives an estimator that can predict such quantities. The estimator is derived via inequalities and matrix norms, and the resulting quantity is roughly analogous to a condition number for the entire neural network. An approximation of the estimator is tested on two Convolutional Neural Networks, AlexNet and VGG-19, using the ImageNet dataset. For each of these networks, the tightness of the estimator is explored via random perturbations and adversarial attacks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.12679>)

[PDF](<https://arxiv.org/pdf/2307.12679.pdf>)