Machine Learning

Terminal Veracity: How Russian Propaganda Uses Telegram to Manufacture ‘Objectivity’ on the Battlefield

Abstract:

This article investigates over 130,000 Telegram messages, 15,000 Telegram forwards, and 750 news articles from Russian-affiliated media to assess the information supply chain between Russian media and Telegram channels covering the war in Ukraine. Using machine-learning techniques, this research provides a framework for conducting argument and network analysis for disambiguating narratives, channels, and users, and mapping dissemination pathways of influence operations. The findings indicate that a central feature of Russian war reporting is actually the prevalence of neutral, non-argumentative language. Moreover, dissemination patterns between media sites and Telegram channels reveal a well-cited information laundering network with a distinct supply chain of covert, semi-covert, and overt channel types active at seed, copy, and amplification levels of operation.

Published In

Volume 23, Issue 3

Navigating the First Year of the Ukrainian Battlefield: Machine Learning vs. Large Language Models

Abstract:

In an era marked by impressive technological developments, conflicts persist and are rooted in complex historical and socioeconomic dynamics, also manifesting through social media platforms. While the war in Ukraine garnered global attention and prompted humanitarian and strategic responses, more efforts are necessary to understand its dynamics and implications directly by analysing the discourses of Ukrainian people in raising unconventional social media platforms like Telegram and TikTok. Accordingly, this research deploys a Data Science approach for building a set of Machine Learning and Large Language Models for analysing discourses and sentiments of Ukrainian users in the first year of war.

Published In

Volume 23, Issue 2

Data-Driven Model Generation for Deception Defence of Cyber-Physical Environments

Abstract:

Cyber deception is a burgeoning defence technique that provides increased detection and slowed attack impact. Deception could be a valuable solution for defending the slow-to-patch and minimally cryptographic industrial Cyber-Physical Systems. However, it is necessary for cyber- physical decoys to appear connected to the physical process of the defended system to be convincing. In this paper, the authors present a machine-learning approach to learn good-enough models of the defended system to drive realistic decoy response. The results of studying this approach with simulated and real building systems are discussed.

Published In

Volume 20, Issue 2

Human Rights and Artificial Intelligence: A Universal Challenge

Abstract:

As artificially intelligent systems benefit citizens around the globe, there remain many ethical questions about the intrusion of AI into every aspect of our private and professional lives. This paper raises awareness of the unprecedented challenge that governments and private industry face in managing these complex systems that include regulators, markets, and special interests. 

Published In

Volume 20, Issue 1

Written By

Virginia Greiman

Adversarial Attack’s Impact on Machine Learning Model in Cyber-Physical Systems

Abstract: 

Deficiency of correctly implemented and robust defence leaves Internet of Things devices vulnerable to cyber threats, such as adversarial attacks. A perpetrator can utilize adversarial examples when attacking Machine Learning models used in a cloud data platform service. Adversarial examples are malicious inputs to ML-models that provide erroneous model outputs while appearing to be unmodified. This kind of attack can fool the classifier and can prevent ML-models from generalizing well and from learning high-level representation; instead, the ML-model learns superficial dataset regularity. This study focuses on investigating, detecting, and preventing adversarial attacks towards a cloud data platform in the cyber-physical context.

Published In

Volume 19, Issue 4

Attack Scenarios in Industrial Environments and How to Detect Them: A Roadmap

Abstract: 

Cyberattacks on industrial companies have increased in the last years. The Industrial Internet of Things increases production efficiency at the cost of an enlarged attack surface. Physi-cal separation of productive networks has fallen prey to the paradigm of interconnectivity, present-ed by the Industrial Internet of Things. This leads to an increased demand for industrial intrusion detection solutions. There are, however, challenges in implementing industrial intrusion detection. There are hardly any data sets publicly available that can be used to evaluate intrusion detection algorithms. The biggest threat for industrial applications arises from state-sponsored and crim-inal groups.

Published In

Volume 19, Issue 3

Moving Big-Data Analysis from a ‘Forensic Sport’ to a ‘Contact Sport’ Using Machine Learning and Thought Diversity

ABSTRACT

Data characterization, trending, correlation, and sense making are almost always performed after the data is collected. As a result, big-data analysis is an inherently forensic (after-the-fact) process. In order for network defenders to be more effective in the big-data collection, analysis, and intelligence reporting mission space, first-order analysis (initial characterization and correlation) must be a contact sport—that is, must happen at the point and time of contact with the data—on the sensor. This paper will use actionable examples: (1) to advocate for running Machine-Learning (ML) algorithms on the sensor as it will result in more timely, more accurate (fewer false positives), automated, scalable, and usable analyses; (2) discuss why establishing thought-diverse (variety of opinions, perspectives, and positions) analytic teams to perform and produce analysis will not only result in more effective collection, analysis, and sense making, but also increase network defenders’ ability to counter and/or neuter adversaries’ ability to deny, degrade, and destabilize U.S. networks.

Published In

Volume 14, Issue 2

Journal of Information Warfare

The definitive publication for the best and latest research and analysis on information warfare, information operations, and cyber crime. Available in traditional hard copy or online.

Keywords

(

2

3

4

8

9

A
AI
APT

a

B

C
C2
C2S
CDX
CIA
CIP
CPS

D
DNS
DoD
DoS

E

e

F

G

H

I
IA
ICS

i

J

K

L

M

N

O

P
PDA

Q

R

S
SOA

T

t

U

V

W

X
XRY

Y

Z

Quill Logo

The definitive publication for the best and latest research and analysis on information warfare, information operations, and cyber crime. Available in traditional hard copy or online.

SUBSCRIBE NOW

Get in touch

Registered Agent and Mailing Address

  • Journal of Information Warfare
  •  ArmisteadTEC
  • Dr Leigh Armistead, President
  • 1624 Wakefield Drive
  • Virginia Beach, VA 23455

 757.510.4574

 JIW@ArmisteadTec.com