Date of Award

9-2022

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Department of Electrical and Computer Engineering

First Advisor

Scott R. Graham, PhD

Abstract

Modern multi-tasking computer systems run numerous applications simultaneously. These applications must share hardware resources including the Central Processing Unit (CPU) and memory while maximizing each application’s performance. Tasks executing in this shared environment leave residue which should not reveal information. This dissertation applies machine learning and statistical analysis to evaluate task residue as footprints which can be correlated to identify tasks. The concept of privilege strata, drawn from an analogy with physical geology, organizes the investigation into the User, Operating System, and Hardware privilege strata. In the User Stratum, an adversary perspective is taken to build an interrogator program that creates footprints in an isolated environment (e.g., containers or sandboxes) to classify applications with up to 100% accuracy under Simultaneous Multithreading (SMT) conditions. In the Operating System Stratum, a framework was developed to collect labeled microprocessor performance data on Intel and IBM processors with microsecond coarseness to characterize the data behavior as a time series. Finally, the Hardware Stratum established a novel data collection approach to extract long sequences from a RISC-V processor to design an expert classifier with a balanced accuracy score of 0.8553 when implemented on a Xilinx Virtex6 Field Programmable Gate Array (FPGA). This research shows that footprints can be correlated to identify tasks in each privilege stratum but also finds that application load reduces the effectiveness of the correlation techniques examined.

AFIT Designator

AFIT-ENG-DS-22-S-024

Share

COinS