Hardware Assisted Stealthy Diversity (CHECKMATE)

Abstract

CHECKMATE hardens homogenous computing environments from attacks through massive diversification of application execution. The CHECKMATE proof-of-concept prototype achieves diversification by leveraging underutilized silicon in today's computer systems such as unused memory, extra processor cores, and other underutilized processors such as graphical processing units (GPUs). Specifically, CHECKMATE introduces diversity in application execution by weaving the execution of many unique but functionally equivalent instruction streams representing an application. By introducing diversity at execution time, CHECKMATE greatly increases the effort required by an adversary to mount an attack against a system with little impact on performance. A successful attack against a CHECKMATE-enabled system would require successfully guessing the correct mixture of instruction streams and architectures before they are chosen at execution time. The combinatorial explosion of possible execution paths and architectural variation makes a successful navigation very improbable even with prior knowledge of the system components or the ability to guess at high speed. CHECKMATE is applicable to a wide-range of applications from embedded systems to commodity devices and has been shown to exhibit quantifiable security benefits.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2013
Accession Number
ADA590378

Entities

People

  • Hina Mccree
  • Joshua Edmison

Organizations

  • RTX

Tags

Communities of Interest

  • Cyber
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Code Injection
  • Coding
  • Computer Architecture
  • Computer Programming
  • Computer Programs
  • Computers
  • Decoding
  • Domain Specific Programming Languages
  • Embedded Systems
  • Instruction Set Architecture
  • Instructions
  • Operating Systems
  • Security
  • Web Browsers

Fields of Study

  • Computer science

Readers

  • Internal Combustion Engine (ICE) Technology.
  • Parallel and Distributed Computing.