Erik Hemberg
Erik Hemberg 01/01
Dr. Erik Hemberg is a Research Scientist in the Anyscale Learning For All (ALFA) group at the Computer Science and Artificial Intelligence Laboratory at Massachusetts Institute of Technology, Cambridge, US. Dr. Hemberg has over 15 years of award-winning expertise in the research, development and application of Artificial Intelligence, Machine Learning and Data Science to improve performance in the fields of cybersecurity, program synthesis, tax compliance, education, and neuroscience. He has a PhD in Computer Science from University College Dublin, Ireland and a MSc in Industrial Engineering and Management from Chalmers University of Technology, Sweden.
Keynote: Proactive Cyber Defense with Artificial Intelligence
Proactive cyber defense could improve security, e.g. through cyber hunting. Defending against diverse, dynamic threats requires linked knowledge of threats, vulnerabilities, and mitigations. Cyber analysts and hunters use this knowledge to trace threats from observed indicators—and, conversely, to identify likely indicators from known threats. Threat modelers rely on it to explore and prioritize mitigations. We have aggregated public cyber threat knowledge into a property graph, enriching sources that currently expose only limited, unidirectional links. This property graph could make it easier for analysts and automated systems to answer key questions. To further increase utility, we apply Artificial Intelligence both to enhance the data and to inform test and evaluation of computer networks. This talk exposes the insights gained from my studies of adversarial engagements in multiple different environments, from tax avoidance to malware detection, and also discusses how it affects current and future challenges.