arXiv · 2611.14594
Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball
Abstract
Adversarial Machine Learning research is currently centered on the search for the epsilon-ball: minimal perturbations designed to fool models while remaining imperceptible to humans. We argue that this fixation on $\ell_p$ norms is a metrological trap that communicates a distorted perception of risk to defenders, one that is unaligned with real-world system vulnerabilities. This paradigm misleads defenders into optimizing for narrow, mathematical robustness at the expense of systemic security, while simultaneously incentivizing attackers to exploit non-overlapping alternative adversarial pathways. Ultimately, we argue that the dominance of the $\ell_p$ ball does not just fail to reduce harm---it may actively facilitate it by communicating a false sense of security against the wrong threats.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Andrew C. Cullen, Neil G. Marchant, Paul Montague, Jiani Xie, Benjamin I. P. Rubinstein. 2026-11-10. Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball. https://searcharxiv.com/abs/2611.14594
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.