In 2026, still no adversarially robust model on CIFAR-10 (73.7% cap)

maksym_andr · x · 2026-11-22

Maksym Andrusiv notes that in 2026 there's still no adversarially robust model on CIFAR-10. RobustBench's ℓ∞=8/255 leaderboard caps at 73.7% robust accuracy (ICML 2024 scaling-law study using 300M extra synthetic images), leaving a 20-point gap to standard accuracy. RobustBench standardizes evaluation with AutoAttack across 3,000+ papers and open-sources the models.

Original post →

More from Research

Research channel →