Trustworthy Machine Learning under Social and Adversarial Data Sources

Machine learning has witnessed remarkable breakthroughs in recent years. Many machine learning techniques assume that the training and test data are sampled from an underlying distribution and aim to find a predictor with low population loss. However, in the real world, data may be generated by strategic individuals, collected by self-interested data collectors, possibly poisoned by adversarial attackers, and used to create predictors, models, and policies satisfying multiple objectives. As a result, predictors may underperform. To ensure the success of machine learning, it is crucial to develop trustworthy algorithms capable of handling these factors.