posted on 2024-10-15, 13:16authored bySaeed Mahloujifar, Xiao ZhangXiao Zhang, Mohammad Mahmoody, David Evans
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 Ω(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 L-infinity and L2 perturbations of several image classification benchmarks. Code for our experiments is available at https://github.com/xiaozhanguva/Measure-Concentration.
History
Primary Research Area
Trustworthy Information Processing
Name of Conference
Conference on Neural Information Processing Systems (NeurIPS)
CISPA Affiliation
No
BibTeX
@conference{Mahloujifar:Zhang:Mahmoody:Evans:2019,
title = "Empirically Measuring Concentration: Fundamental Limits to Intrinsic Robustness",
author = "Mahloujifar, Saeed" AND "Zhang, Xiao" AND "Mahmoody, Mohammad" AND "Evans, David",
year = 2019,
month = 12
}