SLiR parameterizes linear relaxations by slope and uses shifting to compute sound bounds for general activation functions, enabling up to 7.8x more verified properties than prior methods.
Fastened CROWN: tightened neural network robustness certificates,
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
-
Shifting-based Optimizable Linear Relaxations for General Activation Functions
SLiR parameterizes linear relaxations by slope and uses shifting to compute sound bounds for general activation functions, enabling up to 7.8x more verified properties than prior methods.