Una-May O'Reilly is leader of the AnyScale Learning For All (ALFA) group at CSAIL. ALFA focuses on scalable machine learning, evolutionary algorithms, and frameworks for large scale knowledge mining, prediction and analytics. The group has projects in cybersecurity, healthcare, and online education.

Una-May's talk is titled 'Data Science and Machine Learning Toward Artificial Adversarial Intelligence' and will be followed by a Q&A session.

Humans frequently compete with one another. They sometimes develop adversarial systems. And, they often cooperate to take on a common foe. My interest in Artificial Adversarial Intelligence has led me to cyber security and data science, where I further apply evolutionary computation and other machine learning techniques. There are multiple text-based data sources that record, organize, and (partially) link cyber threats, targets, and threat mitigations. My team uses these to simulate competitive coevolutionary dynamics. This provides an anticipatory lens, helping defenders work better on prevention. We are also employing natural language processing to make sense of the text in the entries of these sources. On the basis of textual information, supervised ML helps us infer links across entries in different sources that may exist but which are either undocumented, unobserved, or which should be anticipated. This helps cyber defense personnel to work more efficiently and receive machine-inferred knowledge that they could not derive themselves given the volume of the data sources.

You can view previous seminars from the Institute of Data Science and AI here.

The Institute for Data Science and Artificial Intelligence is part of the Digital Futures research platform at The University of Manchester.