Bias in Machine Learning and Diversity; Fooling Question Answering Deep Learning Models with TextAttack

Srujan Joshi
With the rise of Machine Learning solutions in the past decade, a major problem that has arisen is that of bias in these solutions. Most often bias in ML models stems from bias in training data and it reveals itself in the form of inequitable predictions. One of the technical solutions to bias is Adversarial Machine Learning. This is a methodology which involves “attacking” (making modifications to) the input data in order to “fool” the...
This data repository is not currently reporting usage information. For information on how your repository can submit usage information, please see our documentation.