An introductory preview of Autonomous Intelligent Cyber-defense
Agent reference architecture, release 2.0

J 2020

An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0

KOTT, Alexander, Paul THERON, Luigi MANCINI, Edlira DUSHKU, Agostino PANICO et. al.

Basic information

Original name

An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0

Authors

KOTT, Alexander (840 United States of America), Paul THERON (250 France), Luigi MANCINI, Edlira DUSHKU, Agostino PANICO, Martin DRAŠAR (203 Czech Republic, guarantor, belonging to the institution), Benoit LEBLANC, Paul LOSIEWICZ, Alessandro GUARINO, Mauno PIHELGAS and Krzysztof RZADCA

Edition

The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology, THOUSAND OAKS, SAGE PUBLICATIONS INC, 2020, 1548-5129

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

RIV identification code

RIV/00216224:14610/20:00118543

Organization unit

Institute of Computer Science

DOI

http://dx.doi.org/10.1177/1548512919886163

UT WoS

000496078600001

Keywords in English

Intelligent agent; autonomy; cyber warfare; cyber defense; agent architecture

Abstract

V originále

The North Atlantic Treaty Organization (NATO) Research Task Group IST-152 developed a concept and a reference architecture for intelligent software agents performing active, largely autonomous cyber-defense actions on military assets. The group released a detailed report, briefly reviewed in this article, where such an agent is referred to as an Autonomous Intelligent Cyber-defense Agent (AICA). In a conflict with a technically sophisticated adversary, NATO military networks will operate in a heavily contested battlefield. Enemy malware will likely infiltrate and attack friendly networks and systems. Today's reliance on human cyber defenders will be untenable on the future battlefield. Instead, artificially intelligent agents, such as AICAs, will be necessary to defeat the enemy malware in an environment of potentially disrupted communications where human intervention may not be possible. The IST-152 group identified specific capabilities of AICA. For example, AICA will have to be capable of autonomous planning and execution of complex multi-step activities for defeating or degrading sophisticated adversary malware, with the anticipation and minimization of resulting side effects. It will have to be capable of adversarial reasoning to battle against a thinking, adaptive malware. Crucially, AICA will have to keep itself and its actions as undetectable as possible, and will have to use deceptions and camouflage. The report identifies the key functions and components and their interactions for a potential reference architecture of such an agent, as well as a tentative roadmap toward the capabilities of AICA.

Links

EF16_019/0000822, research and development project

Name: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur

Citovat

KOTT, Alexander, Paul THERON, Luigi MANCINI, Edlira DUSHKU, Agostino PANICO, Martin DRAŠAR, Benoit LEBLANC, Paul LOSIEWICZ, Alessandro GUARINO, Mauno PIHELGAS and Krzysztof RZADCA. An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0. The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology. THOUSAND OAKS: SAGE PUBLICATIONS INC, 2020, vol. 17, No 1, p. 51-54. ISSN 1548-5129. Available from: https://dx.doi.org/10.1177/1548512919886163.

@article{1763778,
   author = {Kott, Alexander and Theron, Paul and Mancini, Luigi and Dushku, Edlira and Panico, Agostino and Drašar, Martin and LeBlanc, Benoit and Losiewicz, Paul and Guarino, Alessandro and Pihelgas, Mauno and Rzadca, Krzysztof},
   article_location = {THOUSAND OAKS},
   article_number = {1},
   doi = {http://dx.doi.org/10.1177/1548512919886163},
   keywords = {Intelligent agent; autonomy; cyber warfare; cyber defense; agent architecture},
   language = {eng},
   issn = {1548-5129},
   journal = {The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology},
   title = {An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0},
   url = {https://journals.sagepub.com/doi/10.1177/1548512919886163},
   volume = {17},
   year = {2020}
}

TY  - JOUR
ID  - 1763778
AU  - Kott, Alexander - Theron, Paul - Mancini, Luigi - Dushku, Edlira - Panico, Agostino - Drašar, Martin - LeBlanc, Benoit - Losiewicz, Paul - Guarino, Alessandro - Pihelgas, Mauno - Rzadca, Krzysztof
PY  - 2020
TI  - An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0
JF  - The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology
VL  - 17
IS  - 1
SP  - 51-54
EP  - 51-54
PB  - SAGE PUBLICATIONS INC
SN  - 15485129
KW  - Intelligent agent
KW  - autonomy
KW  - cyber warfare
KW  - cyber defense
KW  - agent architecture
UR  - https://journals.sagepub.com/doi/10.1177/1548512919886163
N2  - The North Atlantic Treaty Organization (NATO) Research Task Group IST-152 developed a concept and a reference architecture for intelligent software agents performing active, largely autonomous cyber-defense actions on military assets. The group released a detailed report, briefly reviewed in this article, where such an agent is referred to as an Autonomous Intelligent Cyber-defense Agent (AICA). In a conflict with a technically sophisticated adversary, NATO military networks will operate in a heavily contested battlefield. Enemy malware will likely infiltrate and attack friendly networks and systems. Today's reliance on human cyber defenders will be untenable on the future battlefield. Instead, artificially intelligent agents, such as AICAs, will be necessary to defeat the enemy malware in an environment of potentially disrupted communications where human intervention may not be possible. The IST-152 group identified specific capabilities of AICA. For example, AICA will have to be capable of autonomous planning and execution of complex multi-step activities for defeating or degrading sophisticated adversary malware, with the anticipation and minimization of resulting side effects. It will have to be capable of adversarial reasoning to battle against a thinking, adaptive malware. Crucially, AICA will have to keep itself and its actions as undetectable as possible, and will have to use deceptions and camouflage. The report identifies the key functions and components and their interactions for a potential reference architecture of such an agent, as well as a tentative roadmap toward the capabilities of AICA.
ER  -

KOTT, Alexander, Paul THERON, Luigi MANCINI, Edlira DUSHKU, Agostino PANICO, Martin DRAŠAR, Benoit LEBLANC, Paul LOSIEWICZ, Alessandro GUARINO, Mauno PIHELGAS and Krzysztof RZADCA. An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0. \textit{The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology}. THOUSAND OAKS: SAGE PUBLICATIONS INC, 2020, vol.~17, No~1, p.~51-54. ISSN~1548-5129. Available from: https://dx.doi.org/10.1177/1548512919886163.

Detailed Information on Publication Record