A solution-aware ReLU scoring function selects the few binary ReLU variables that matter, letting a hybrid MILP verifier cut undecided robustness instances from 20-58% to 8-15%.
Adversarial training and provable de- fenses: Bridging the gap
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Solution-aware vs global ReLU selection: partial MILP strikes back for DNN verification
A solution-aware ReLU scoring function selects the few binary ReLU variables that matter, letting a hybrid MILP verifier cut undecided robustness instances from 20-58% to 8-15%.