The Role of Randomization in Trustworthy Machine Learning
Nicolas Papernot · 2022
Machine learning has been perhaps this decade's most significant technological development, with the prospect of becoming a general-purpose technology. Applications range from autonomous driving to assisting with court decisions. In many of these settings, the worst-case performance of machine learning is critical. Yet, the predictions of machine learning often appear fragile, with no hint as to the reasoning behind them-and may be dangerously wrong. This situation is in large part due to the absence of security considerations in the design of machine learning algorithms. This is unacceptable: society must be able to trust and hold machine learning accountable.