Elisabeth Baseman

TL;DR: An anomaly detection framework that combines graph analysis, relational learning, and kernel density estimation to detect unusual syslog messages and retrieves anomalous behaviors inserted into syslog files from a virtual machine is presented.

TL;DR: A sufficiently sophisticated software fault injection framework, an application can be studied to see how it would handle many of the errors that manifest at the application level, and a developer can progressively improve the resilience at targeted locations they believe are important for their target hardware.

TL;DR: This work explores the predictive performance of an online machine learning-based approach in classifying DRAM fault modes from two leadership-class supercomputing facilities and provides a critical analysis of this online learning technique that can benefit system designers to help inform best practices for dealing with reliability on future systems.

TL;DR: This work learns a Markov chain model from average case system logs and uses it to generate synthetic system log data and explores the abilities of this learned model to identify anomalous behavior by evaluating its ability to catch inserted and missing log messages.