# Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness

Source: [Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness](<https://www.sota2.com/research/paper/68fa56551e209131ce99bdc8>)

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

Data updated: 2025-10-25T14:05:48.848Z

Authors: Saeed Mahloujifar, Xiao Zhang, Mohammad Mahmoody, David Evans

Published: 2019-05-29T03:51:34.000Z

## Abstract

Many recent works have shown that adversarial examples that fool classifiers can be found by minimally perturbing a normal input. Recent theoretical results, starting with Gilmer et al. (2018b), show that if the inputs are drawn from a concentrated metric probability space, then adversarial examples with small perturbation are inevitable. A concentrated space has the property that any subset with $\\Omega(1)$ (e.g., 1/100) measure, according to the imposed distribution, has small distance to almost all (e.g., 99/100) of the points in the space. It is not clear, however, whether these theoretical results apply to actual distributions such as images. This paper presents a method for empirically measuring and bounding the concentration of a concrete dataset which is proven to converge to the actual concentration. We use it to empirically estimate the intrinsic robustness to $\\ell\_\\infty$ and $\\ell\_2$ perturbations of several image classification benchmarks. Code for our experiments is available at https://github.com/xiaozhanguva/Measure-Concentration.

## 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/1905.12202>)

[PDF](<https://arxiv.org/pdf/1905.12202.pdf>)
