"Proving Data-Poisoning Robustness in Decision Trees," by Samuel Drews et al., addresses the challenge of processing an intractably large set of trained models...Martin Vechev From Communications of the ACM | February 2023
We present a sound verification technique based on abstract interpretation and implement it in a tool called Antidote, which abstractly trains decision trees for...Samuel Drews, Aws Albarghouthi, Loris D'Antoni From Communications of the ACM | February 2023