Attacking RF Machine Learning Systems

Abstract

The VT Hume Center proposes to develop both foundational and applied research results aimed at blind characterization and optimal attack methods against RF machine learning systems, to include attacks on wideband (500 MHz) blind signal classification, ML-infused DSA algorithms, ML-trained behaviors generalized to match time-varying channel conditions, and specific emitter identification techniques. We will also explore battle damage assessment of an adversary’s ML-based RF system.

Document Details

Document Type
DoD Grant Award
Publication Date
Oct 09, 2018
Source ID
N001741810005

Entities

People

  • Alan J. Michaels

Organizations

  • United States Navy
  • Virginia Tech

Tags

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Radio communications and signal processing.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks