Nave Frost

Personal insights for altering decisions of tree-based ensembles over time

2020 · Proceedings of the VLDB Endowment

Machine Learning models are prevalent in critical human-related decision making, such as resume filtering and loan applications. Refused individuals naturally ask what could change the decision, should they reapply. This question is hard for the …

CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers

2024

This work presents CaFA, a system for Cost-aware Feasible Attacks for assessing the robustness of neural tabular classifiers against adversarial examples realizable in the problem space, while minimizing adversaries’ effort. To this end, CaFA leverages …