Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2021 | Buch

Introduction Kapitel lesen Erstes Kapitel lesen

A Machine Learning Based Model of Boko Haram

verfasst von: Prof. V. S. Subrahmanian, Ph.D. Chiara Pulice, James F. Brown, Jacob Bonen-Clark

Verlag: Springer International Publishing

Buchreihe : Terrorism, Security, and Computation

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This is the first study of Boko Haram that brings advanced data-driven, machine learning models to both learn models capable of predicting a wide range of attacks carried out by Boko Haram, as well as develop data-driven policies to shape Boko Haram’s behavior and reduce attacks by them. This book also identifies conditions that predict sexual violence, suicide bombings and attempted bombings, abduction, arson, looting, and targeting of government officials and security installations.

After reducing Boko Haram’s history to a spreadsheet containing monthly information about different types of attacks and different circumstances prevailing over a 9 year period, this book introduces Temporal Probabilistic (TP) rules that can be automatically learned from data and are easy to explain to policy makers and security experts. This book additionally reports on over 1 year of forecasts made using the model in order to validate predictive accuracy. It also introduces a policy computation method to rein in Boko Haram’s attacks.

Applied machine learning researchers, machine learning experts and predictive modeling experts agree that this book is a valuable learning asset. Counter-terrorism experts, national and international security experts, public policy experts and Africa experts will also agree this book is a valuable learning tool.

Inhaltsverzeichnis

Frontmatter
Chapter 1. Introduction
Abstract
Boko Haram is one of the deadliest terrorist groups in the world today. This chapter provides a quick overview of several major types of attacks carried out by Boko Haram since its inception. The chapter also describes the factors that are predictively linked to various types of attacks carried out over a future time window of 1, 2, 3, 4, 5, and 6 months. The chapter describes a set of policies that show promise of reducing violence by Boko Haram, together with a detailed analysis of one policy in particular.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 2. History of Boko Haram
Abstract
In this chapter we will go over Boko Haram’s origins and examine the group’s decade long campaign of terror. We will explore some background information about Nigeria as well as the conditions that led up to the establishment of Boko Haram. We then cover the history of the group from its founding to the present day. In later sections of this chapter we discuss how and where the group operates. In addition, we explore some of the relationships the group has with outside terrorist groups.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 3. Temporal Probabilistic Rules and Policy Computation Algorithms
Abstract
In this chapter, we briefly describe the science underlying the temporal probabilistic (TP) rule paradigm for explaining the behavior of terrorist groups such as Boko Haram. We present the syntax and semantics of TP-rules informally, together with a brief sketch of algorithms to extract such rules. Given a set of TP-rules governing the behavior of a group as input, we also present a method to extract policies that prevent attacks by the group.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 4. Sexual Violence
Abstract
Boko Haram’s use of sexual violence has been one of the group’s hallmarks. In almost half of the months examined, an act of sexual violence was perpetrated by the group. This chapter will discuss the circumstances related to the occurrence of sexual violence as well as the circumstances which are linked to a lack of sexual violence for a given month. For example, our findings show how a lack of explicit advocacy for religious rule in a given month can be linked to sexual violence in the months that follow.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 5. Suicide Bombings
Abstract
Suicide bombings have been one of Boko Haram’s go-to tools of terror after the group escalated its campaign of violence. During 2015 and 2016 only one month during each year did not see a suicide bombing. This chapter will examine the circumstances surrounding suicide bombings and the temporal probabilistic rules (TP-Rules) we were able to derive. These TP-Rules were derived from the circumstances and events that appear to be linked to Boko Haram’s use of suicide bombers. For example, we derived TP-Rules to predict the occurrence or absence of suicide bombings based on Boko Haram’s use of child soldiers.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 6. Abductions
Abstract
Abductions have been one of Boko Haram’s key terror strategies. The group targets children in particular and UNICEF estimates that more than 1000 children have been abducted by the group since 2013. The persons abducted by Boko Haram face a variety of horrors. Some are forced to be the brides of fighters while others are used as bargaining chips at the negotiating table. Most horrific are those hostages brainwashed or coerced into becoming suicide bombers for the group. The work presented in this chapter presents the temporal probabilistic rules (TP-Rules) we derived to predict abductions months in advance. These rules were derived by examining the circumstance surrounding when Boko Haram abducts people.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 7. Arson
Abstract
Boko Haram has used arson for years in its war of terror. The group has torched villages in its campaign to bring sharia law to northeastern Nigeria. In February of 2016, Boko Haram razed the village of Dalori killing 80 people. Those killed in attacks like this are not the only victims. Those whose homes are burnt are displaced and have no other option but to flee to camps for displaced people. People spend years in these camps and live in deplorable conditions (Mohamed H. Thousands displaced by Boko Haram languish in Abuja IDP camps. Aljazeera. https://​www.​aljazeera.​com/​indepth/​features/​thousands-displaced-boko-haram-languish-abuja-idp-camps-180325070133915.​html. Accessed 12 Feb 2019, 2018). The goal of this chapter is to present some of the temporal probabilistic rules (TP-Rules) we have developed to predict the occurrence of arson. We also discuss the circumstances surrounding Boko Haram’s arson attacks. By deriving these TP-Rules, our aim is to combat Boko Haram’s campaign of terror.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Chapter 8. Other Types of Attacks
Abstract
In this chapter, we will discuss TP-rules that we have derived involving the following types of attacks by Boko Haram: the targeting of government officials, looting, the targeting of security installations, and attempted bombings. For the targeting of government officials, looting, and attempted bombings we will discuss the rules we derived to predict the occurrence of these events. For the targeting of security installations, we will look at TP-Rules that we derived to predict an absence of this event. At the end of the chapter we will also report the performance of our predictive models for each event.
V. S. Subrahmanian, Chiara Pulice, James F. Brown, Jacob Bonen-Clark
Backmatter
Metadaten
Titel
A Machine Learning Based Model of Boko Haram
verfasst von
Prof. V. S. Subrahmanian
Ph.D. Chiara Pulice
James F. Brown
Jacob Bonen-Clark
Copyright-Jahr
2021
Electronic ISBN
978-3-030-60614-5
Print ISBN
978-3-030-60613-8
DOI
https://doi.org/10.1007/978-3-030-60614-5

Premium Partner

    Bildnachweise