Ethical Testing in the Real World: Evaluating Physical Testing of Adversarial Machine Learning

TL;DR

This paper critically examines the adequacy of physical testing in adversarial machine learning against computer vision, highlighting ethical concerns and proposing improvements for more representative real-world testing.

Contribution

It introduces a critique of current physical testing practices in adversarial ML and offers recommendations to enhance testing representativeness and ethical standards.

Findings

Physical testing in adversarial ML is often minimal and unrepresentative.

Many studies lack detailed reporting on testing procedures and subjects.

Improved physical testing can mitigate ethical and safety issues.

Abstract

This paper critically assesses the adequacy and representativeness of physical domain testing for various adversarial machine learning (ML) attacks against computer vision systems involving human subjects. Many papers that deploy such attacks characterize themselves as "real world." Despite this framing, however, we found the physical or real-world testing conducted was minimal, provided few details about testing subjects and was often conducted as an afterthought or demonstration. Adversarial ML research without representative trials or testing is an ethical, scientific, and health/safety issue that can cause real harms. We introduce the problem and our methodology, and then critique the physical domain testing methodologies employed by papers in the field. We then explore various barriers to more inclusive physical testing in adversarial ML and offer recommendations to improve such testing notwithstanding these challenges.