Adversarial distillation improves student robustness when teachers show high uncertainty on robustly unlearnable samples, suppressing noise memorization and allowing reliance on learnable robust signals.
Post-T0 Control on Learnable Samples Once the signal reaches its target scale at time T0, learnable samples no longer drive large updates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Understanding Adversarial Distillation: Why Robust Teachers Fail
Adversarial distillation improves student robustness when teachers show high uncertainty on robustly unlearnable samples, suppressing noise memorization and allowing reliance on learnable robust signals.