Debate: with ~1/255 Linf budgets on CIFAR-10, adversarial examples mostly vanish

scaling01 · x · 2026-11-23

@maksymandr argued that whether adversarial examples remain a problem depends on the perturbation budget: at 1/255 Linf on CIFAR-10, you wouldn't find adversarial examples (or only for very few images). scaling01 agreed once budgets are included, noting this implies models likely have more headroom to improve. A concise exchange highlighting that many "models are easily fooled" conclusions rest on looser perturbation budgets.

Related event: Researchers Debate Adversarial Examples: Robustness Hinges on Perturbation Budget(3 posts)→

Original post →

More from Research

Research channel →