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

arXiv: https://arxiv.org/abs/2012.02048 · HTML: https://mlsanity.com/paper/2012.02048/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks](https://mlsanity.com/paper/2107.10302/) (2021)
- [A Conceptual Framework for Ethical Evaluation of Machine Learning Systems](https://mlsanity.com/paper/2408.10239/) (2024)
- [Area is all you need: repeatable elements make stronger adversarial attacks](https://mlsanity.com/paper/2306.07768/) (2023)

## Abstract (arXiv)

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.