Anjalie Field 2024 Early Career Fellow
Affiliation Assistant Professor, Johns Hopkins University Hard Problem Solved AI’s continually evolving safety and security, robustness, performance, output challenges and other shortcomings that may cause harm or erode public trust of AI systems, especially in safety-critical applications and uses where societal stakes and potential for societal harm are high.

Anjalie Field is an Assistant Professor in the Computer Science Department, Whiting School of Engineering at Johns Hopkins University. She is also affiliated with the Center for Language and Speech Processing (CLSP). Her research focuses on the ethics and social science aspects of natural language processing, which includes developing AI models to address societal issues like discrimination and propaganda, as well as critically assessing and improving ethics in AI pipelines. Prior to joining JHU, she was a postdoctoral researcher in the Stanford NLP Group and Stanford Data Science Institute working with Dan Jurafsky and Jennifer Eberhardt. She completed her PhD at the Language Technologies Institute at Carnegie Mellon University, advised by Yulia Tsvetkov.

AI2050 Project

Modern AI models are prone to memorizing and leaking sensitive information from training data, such as names or addresses. This tendency makes it unsafe to build and deploy models in high-stakes domains like healthcare or social services. Our work will build new technology to improve privacy in AI, including developing methods to evaluate privacy, to preserve privacy, and to safely incorporate sensitive information in appropriate settings. Ultimately this work will facilitate safer development and deployment of AI and reduce potential societal harms.