Abstract: Today we face an explosion of systems from health monitoring to national security infrastructure that generate and collect vast data daily. Increasingly, these systems use machine learning methods for intelligent decisions, prone to cyber-security attacks. So, we ask how data privacy should be protected in a world where data is gathered and shared with increasing speed and ingenuity.
This presentation will describe several privacy techniques for streaming data protection, frameworks for machine learning, and defense strategies for privacy attacks. We will share results using real-world dataset and ORNL testbed and describe best practices. The talk concludes with a brief discussion of present open challenges in privacy-preserving algorithms and describe several research opportunities relevant for DOE.
Bio: Olivera Kotevska is a Research Scientist in Mathematics in Computations Section in the Computer Science and Mathematics Division (CSMD) at Oak Ridge National Laboratory (ORNL). She received her PhD in Computer Science from University of Grenoble Alpes, France.