When the Learning Sciences emerged in 1991, there was an ethos of studying learning in humans and machines in conjunction with one another. This ethos reflected three decades of prior work on the interdisciplinary study of learning; however, in the three decades since the emergence of the Learning Sciences, it seems to have largely disappeared. I…

Defenses against adversarial attacks are essential to ensure the reliability of machine learning models as their applications are expanding in different domains. Existing ML defense techniques have several limitations in practical use. I proposed a trustworthy framework that employs an adaptive strategy to inspect both inputs and decisions. In…