This page was reviewed but not written by the grant investigators. Berryville Institute of Machine Learning staff also reviewed this page prior to publication.
Open Philanthropy recommended a grant of $150,000 to the Berryville Institute of Machine Learning to support research led by Gary McGraw on machine learning security. The research will focus on building a taxonomy of known attacks on machine learning, exploring a hypothesis of representation and machine learning risk, and performing an architectural risk analysis of machine learning systems. Our potential risks from advanced artificial intelligence team hopes that the research will help advance the field of machine learning security.