Accuracy

As the use of machine learning in high impact domains becomes widespread, the importance of evaluating safety has increased. An important aspect of this is evaluating how robus...

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on p...

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, wh...

We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empiric...

Algorithmic decision making is employed in an increasing number of real-world applicationstions to aid human decision making. While it has shown considerable promise in terms o...

Recently, the following Discrimination-Aware Classification Problem was introduced: Suppose we are given training data that exhibit unlawful discrimination; e.g., towa...

Almost all drift detection mechanisms designed for classification problems work reactively: after receiving the complete data set (input patterns and class labels) they apply a...

Machine-learning (ML) algorithms are increasingly utilized in privacy-sensitive applications such as predicting lifestyle choices, making medical diagnoses, and facial recognit...

This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequenc...

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type ...

The Human-Computer Trust scale (HCTS) is a simple, nine-item attitude Likert scale that gives a global view of subjective assessments of trust in technology.

The HCTS resu...