Machine Learning Security: Foundations and Future
Hyrum Anderson is Distinguished Engineer at Robust Intelligence, focusing on solutions to promote the integrity of machine learning systems. Previously, he conducted Microsoft's first AI Red Team exercises and founded the Microsoft AI Red Team to assess the security and privacy of deployed ML systems. As Chief Scientist at Endgame and Principal Research at Mandiant, he conducted applied research in ML for information security. He also served at Sandia National Laboratories as Principal Staff and Associate Staff at MIT Lincoln Laboratories. He has organized several public competitions to promote the security of ML at http://mlsec.io. He co-founded and sits on the governing board of the Conference on Applied Machine Learning in Information Security (CAMLIS). He received his PhD in Electrical Engineering (Machine Learning + Signal Processing) at the University of Washington, and MS and BS degrees in electrical engineering (Signal and Image Processing + Remote Sensing) at Brigham Young University.