TRAILS: Efficient data flow tracking through hw-assisted parallelization

Abstract

The goal of this effort is to make currently opaque computing systems transparent by providing high-fidelity visibility into component interactions during system operation at the hardware architecture layer, while imposing minimal performance overhead. The scope of this effort is to develop a novel architecture for efficiently performing dynamic data-flow tracking through hardware-assisted parallelization. The goal includes the creation of an execution environment that provides low-overhead, fine-grained, data-flow tracking (DFT) as a utility for security, privacy, and other applications. Trails aims to exploit the parallelism available in modern architectures to improve DFT performance without the demand for more resources than the ones already required to apply it in line with the application.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2019
Accession Number
AD1081339

Entities

People

  • Georgios Portokalidis

Organizations

  • Stevens Institute of Technology

Tags

Communities of Interest

  • Cyber
  • Energy and Power Technologies
  • Engineered Resilient Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Air Force Facilities
  • Air Force Research Laboratories
  • Compilers
  • Computing System Architectures
  • Debugging
  • Decoding
  • Field Programmable Gate Arrays
  • Government Procurement
  • Governments
  • Hash Tables
  • Instruction Set Architecture
  • Instrumentation
  • Intellectual Property
  • Operating Systems
  • Security
  • Virtual Machines

Fields of Study

  • Computer science
  • Engineering

Readers

  • Distributed Systems and Data Platform Development
  • Parallel and Distributed Computing.