東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Machine Learning of Cyberattack and ...

Bland, John Andrew.

Linked to FindBook

Google Book

Amazon

博客來

Machine Learning of Cyberattack and Defense Strategies.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine Learning of Cyberattack and Defense Strategies./
Author:	Bland, John Andrew.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
Description:	206 p.
Notes:	Source: Dissertations Abstracts International, Volume: 80-11, Section: B.
Contained By:	Dissertations Abstracts International80-11B.
Subject:	Computer Engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13877471
ISBN:	9781392120729

Machine Learning of Cyberattack and Defense Strategies.
Bland, John Andrew.

Machine Learning of Cyberattack and Defense Strategies. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 206 p.

Source: Dissertations Abstracts International, Volume: 80-11, Section: B.

Thesis (Ph.D.)--The University of Alabama in Huntsville, 2018.

This item must not be sold to any third party vendors.

Cybersecurity is an increasingly important challenge for computer systems. In this work, cyberattacks were modeled using an extension of the well-known Petri net formalism. That formalism, designated Petri nets with players, strategies, and costs, models the states of the cyberattack and events during the attack as markings and transition firings in the net respectively. The formalism models the attacker and defender as competing players who may observe the marking of a subset of the net and based on the observed marking act by changing the stochastic firing rates of a subset of the transitions in order to achieve their competing goals. Rate changes by the players incur a cost. Using the formalism, nets were constructed to model three specific cyberattack patterns (cross-site scripting, spear phishing, and structured query language injection) documented in the Common Attack Pattern Enumeration and Classification database. The models were validated by a panel of cybersecurity experts in a structured face validation process. Given those validated nets, a reinforcement learning algorithm using an eGreedy policy was implemented and set to the task of learning which actions to take, i.e., which transition rates to change for the different observable markings, so as to accomplish the goals of the attacker or defender. Experiments were conducted with a dynamic (learning) attacker against a static (fixed) defender, a static attacker against a dynamic defender, and a dynamic attacker against a dynamic defender. In all cases, the reinforcement learning algorithm was able to improve its performance, in terms of achieving the player's objective and reducing the cost of doing so, over time. These results demonstrate the potential of formally modeling cyberattacks and of applying reinforcement learning to improving cybersecurity.

ISBN: 9781392120729Subjects--Topical Terms:

1567821
Computer Engineering.

Machine Learning of Cyberattack and Defense Strategies.
LDR:02927nmm a2200325 4500 001 2207896
005 20190923114249.5
008 201008s2018 ||||||||||||||||| ||eng d
020 $a 9781392120729
035 $a (MiAaPQ)AAI13877471
035 $a (MiAaPQ)uah:10510
035 $a AAI13877471
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bland, John Andrew. $3 3434894
245 1 0 $a Machine Learning of Cyberattack and Defense Strategies.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 206 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-11, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Petty, Mikel D.;Morris, Thomas H.
502 $a Thesis (Ph.D.)--The University of Alabama in Huntsville, 2018.
506 $a This item must not be sold to any third party vendors.
520 $a Cybersecurity is an increasingly important challenge for computer systems. In this work, cyberattacks were modeled using an extension of the well-known Petri net formalism. That formalism, designated Petri nets with players, strategies, and costs, models the states of the cyberattack and events during the attack as markings and transition firings in the net respectively. The formalism models the attacker and defender as competing players who may observe the marking of a subset of the net and based on the observed marking act by changing the stochastic firing rates of a subset of the transitions in order to achieve their competing goals. Rate changes by the players incur a cost. Using the formalism, nets were constructed to model three specific cyberattack patterns (cross-site scripting, spear phishing, and structured query language injection) documented in the Common Attack Pattern Enumeration and Classification database. The models were validated by a panel of cybersecurity experts in a structured face validation process. Given those validated nets, a reinforcement learning algorithm using an eGreedy policy was implemented and set to the task of learning which actions to take, i.e., which transition rates to change for the different observable markings, so as to accomplish the goals of the attacker or defender. Experiments were conducted with a dynamic (learning) attacker against a static (fixed) defender, a static attacker against a dynamic defender, and a dynamic attacker against a dynamic defender. In all cases, the reinforcement learning algorithm was able to improve its performance, in terms of achieving the player's objective and reducing the cost of doing so, over time. These results demonstrate the potential of formally modeling cyberattacks and of applying reinforcement learning to improving cybersecurity.
590 $a School code: 0278.
650 4 $a Computer Engineering. $3 1567821
650 4 $a Computer science. $3 523869
690 $a 0464
690 $a 0984
710 2 $a The University of Alabama in Huntsville. $b Electrical and Computer Engineering. $3 2049741
773 0 $t Dissertations Abstracts International $g 80-11B.
790 $a 0278
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13877471