New paper argues adversarial risk research should drop the small epsilon-ball focus
A new arXiv paper in machine learning argues that adversarial machine learning research, centered on minimal epsilon-ball perturbations, needs to move beyond the small epsilon ball in the generative AI era.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-13 05:00 · arXiv cs.LG
Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball