Certified robustness varies extremely across training seeds with std larger than recent gains, and generalizes poorly to unseen data.
Clip- and-verify: Linear constraint-driven domain clipping for accelerating neural network verification,
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
-
On the Extreme Variance of Certified Local Robustness Across Model Seeds
Certified robustness varies extremely across training seeds with std larger than recent gains, and generalizes poorly to unseen data.