no code implementations • 31 Mar 2022 • Giuseppe Castiglione, Gavin Ding, Masoud Hashemi, Christopher Srinivasa, Ga Wu
Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models.
no code implementations • 2 Mar 2022 • Ga Wu, Masoud Hashemi, Christopher Srinivasa
It then complements the negative impact of removing marked data by reweighting the remaining data optimally.
1 code implementation • 24 Aug 2020 • Masoud Hashemi, Ali Fathi
We propose a model criticism and explanation framework based on adversarially generated counterfactual examples for tabular data.