MAML_Poster.pdf

BIO

Daniel Clouse

Education: Phd Universal Algebra, Binghamton University 2002
Work Experience: DoD R&D, Applied Research Mathematician 2002 - Present

ABSTRACT

Machine learning (ML) is proposed as a solution to scalable defensive and offensive capabilities in cyber security. The proposals range from semi-automated decision support tools to fully-automated capabilities. However, ML models can be exploited in at least four ways, poisoning, inversion and extraction. We are developing a framework consisting of a lightweight simulation language, metrics and mitigations to identify ML model design guidelines to improve resiliency against attacks.