To make our lives and systems more secure, Dr. Una-May O’Reilly’s research goals are to understand adversarial intelligence and to computationally model it with machine learning. Dr. O’Reilly hopes that by developing Artificial Adversarial Intelligence it will help reveal the dynamics of conflicting behavior and how adaptation drives it, leading to more secure systems. This is why she works at the intersection of cybersecurity and artificial intelligence.
Dr. O’Reilly, who holds a PhD from Carleton University in Ottawa, Canada and joined CSAIL in 1996, was drawn to this area of research when pursuing her highly regarded and award-winning work on evolutionary algorithms. These algorithms are a good fit to model the evolving arms race between tax avoidance and tax loophole remediation. They supported an approach to identifying vulnerabilities in a subsection of the Internal Revenue code while avoiding auditing, even under auditing co-adaptation. Now one of the main areas Dr. O’Reilly is investigating is cybersecurity and how to stop destructive and escalating arms races between cyber attack actors and cyber defenders.
Another area she is exploring is the security of software. Dr. O’Reilly, who is interested in understanding computer programs in general, conducts neuroscience experiments to reveal how humans read code and uses machine learning models to encode software. Her research also dives into deep learning techniques for program representations. Typically, code varies in length, obeys syntax, and expresses semantics. To automatically detect bugs or code malware, a computer-friendly representation of code that encompasses all of these properties is required. Such representations can be used by software enterprises in machine learning detectors and classification training.
Dr. O’Reilly’s security-driven, adversarial-focused approach to AI and machine learning will lead to more secure systems, better program comprehension, and improved cyber defenses.
BIO
Dr. Una-May O'Reilly is a Senior Research Scientist and the leader of ALFA Group at Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Lab. An AI and Machine Learning researcher for 20+ years, she is broadly interested in Adversarial Intelligence, which refers to the intelligence that develops and is leveraged when learning and adapting within offense-vs-defense environments. Her focus extends to Artificial Adversarial Intelligence, the computational counterpart of this phenomenon. Her fascination with security challenges has led her to explore settings facing cyber threats. She develops deep learning and evolutionary algorithms to model cybersecurity phenomena such as malware detection, cyber hunting, and the dynamic interplay of cyber network attacks and defenses.
Academic accomplishments include an Honorary Doctorate (honoris causa) from Dalhousie University, Canada, multiple Best Paper and Impact awards, more than 200 publications, ACM SIGEVO Recognizing Outstanding Achievements in Evolutionary Computation Award, SPECIES Outstanding Achievements in Evolutionary Computation Award, and multiple keynotes such as ACM SIGEVO Distinguished Lecture at GECCO (2024). She serves on the editorial board of ACM Transactions on Evolutionary Computation and Evolution Computation (MIT Press) and the advisory board of Genetic Programming and Evolvable Machines (Springer).
Una-May holds a B.Sc. from the University of Calgary, and a M.C.S. and Ph.D. (1995) from Carleton University, Ottawa, Canada. She joined the Artificial Intelligence Laboratory, MIT as a Post-Doctoral Associate in 1996.
The MOOC Learner Project provides learning scientists, instructional designers and online education specialists with open source software that enables them to efficiently extract teaching and learning insights from the data collected when students learn on the edX or open edX platform.
Our goal is to help medical researchers and clincians understand the growing repositories of waveform and signal data collected from critically ill patients.
Our goal is to understand the nature of cyber security arms races between malicious and bonafide parties. Our vision is autonomous cyber defenses that anticipate and take measures against counter attacks.
This CoR aims to develop AI technology that synthesizes symbolic reasoning, probabilistic reasoning for dealing with uncertainty in the world, and statistical methods for extracting and exploiting regularities in the world, into an integrated picture of intelligence that is informed by computational insights and by cognitive science.
Our vision is data-driven machine learning systems that advance the quality of healthcare, the understanding of cyber arms races and the delivery of online education.
When a power company wants to build a new wind farm, it generally hires a consultant to make wind speed measurements at the proposed site for eight to 12 months. Those measurements are correlated with historical data and used to assess the site’s power-generation capacity.This month CSAIL researchers will present a new statistical technique that yields better wind-speed predictions than existing techniques do — even when it uses only three months’ worth of data. That could save power companies time and money, particularly in the evaluation of sites for offshore wind farms, where maintaining measurement stations is particularly costly.
By crunching 130 million mouse-clicks, two CSAIL researchers have developed a machine-learning model that can predict with surprising accuracy whether or not a MOOC student will drop out of a given course.
