A student computing security research project guided by PCSD computer scientists Ang Li and Kevin Barker placed third among dozens of entries in the student research poster session at SC19, a premier annual conference for high-performance computing (HPC). The team research project was presented by Pengfei Zou, a graduate student at Clemson University. Zou’s advisor at Clemson University is Rong Ge.
The award honored research using a machine learning framework to identify illicit use of HPC systems. As HPC systems become more powerful, they are increasingly exploited by attackers to run malicious software. The research team showed that the workload classification framework can discern between authorized and illicit workloads with 95 percent accuracy. The research was made possible through the Center for Advanced Technology Evaluation (CENATE), a computing proving ground supported by the U.S. Department of Energy’s Office of Advanced Scientific Computing Research.