ProF repairs DNNs for individual fairness by using interval bound propagation to bound outputs over input sets and solving a MILP to adjust the model with guarantees on those sets.
Formal security analysis of neural networks using symbolic intervals,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Certified robustness varies extremely across training seeds with std larger than recent gains, and generalizes poorly to unseen data.
citing papers explorer
-
Provable Fairness Repair for Deep Neural Networks
ProF repairs DNNs for individual fairness by using interval bound propagation to bound outputs over input sets and solving a MILP to adjust the model with guarantees on those sets.
-
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.