Carnegie Mellon University
Browse
beskow_thesis_FINAL_20200511.pdf (131.3 MB)

Finding and Characterizing Information Warfare Campaigns

Download (131.3 MB)
thesis
posted on 2020-05-15, 14:28 authored by David BeskowDavid Beskow
Today the borderless internet is used by state and non-state actors to manipulate information and societies in ways that were unheard of 50 years ago. Malicious actors can rapidly conduct information maneuvers with little cost at unprecedented scales to achieve far reaching consequences across the internet. They do this by
exploiting features of the various social media platforms and the way humans naturally understand what they read and hear. These cyber-mediated threats to open and
democratic societies have led to an emerging discipline known as social cybersecurity. While various aspects of these campaigns have been explored, little research has
focused on the campaign level of engagement. Our research seeks to answer the question: How can information warfare campaigns be identified and characterized
quickly? Our goal is to 1) Improve understanding of information operations, and 2) Develop techniques to rapidly identify key factors such as bots and memes.
To accomplish this, I present the strategic context of the information warfare that we see today, and identify and define information warfare forms of maneuver. I develop
various supervised and unsupervised methods to identify bots at four different data granularities. I present a deep learning model to classify memes as well as study
the evolution of memes within a conversation. I present a template for understanding the major components of an information campaign and develop automatic ways
to populate this template for a specific event. Finally, we present a Bot, Cyborg, and Troll Field Guide to help analysts and the general population understand these entities.

History

Date

2020-05-15

Degree Type

  • Dissertation

Department

  • Institute for Software Research

Degree Name

  • Doctor of Philosophy (PhD)

Advisor(s)

Kathleen M. Carley

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC