Home > Research > Publications & Outputs > Measuring the Effect of Induced Persona on Agen...

Research

Associated organisational unit

Electronic data

  • SANDMAN (NLPAICS 2024)

    Accepted author manuscript, 357 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

View graph of relations

Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception: Language Agents for Cyber Deception

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Published

Standard

Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception: Language Agents for Cyber Deception. / Newsham, Lewis; Prince, Daniel; Hyland, Ryan.
2024. 48-58 Paper presented at Natural Language Processing and Artificial Intelligence for Cyber Security , Lancaster, United Kingdom.

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Harvard

Newsham, L, Prince, D & Hyland, R 2024, 'Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception: Language Agents for Cyber Deception', Paper presented at Natural Language Processing and Artificial Intelligence for Cyber Security , Lancaster, United Kingdom, 29/07/24 - 30/07/24 pp. 48-58.

APA

Newsham, L., Prince, D., & Hyland, R. (2024). Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception: Language Agents for Cyber Deception. 48-58. Paper presented at Natural Language Processing and Artificial Intelligence for Cyber Security , Lancaster, United Kingdom.

Vancouver

Newsham L, Prince D, Hyland R. Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception: Language Agents for Cyber Deception. 2024. Paper presented at Natural Language Processing and Artificial Intelligence for Cyber Security , Lancaster, United Kingdom.

Author

Newsham, Lewis ; Prince, Daniel ; Hyland, Ryan. / Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception : Language Agents for Cyber Deception. Paper presented at Natural Language Processing and Artificial Intelligence for Cyber Security , Lancaster, United Kingdom.11 p.

Bibtex

@conference{5a562c5bc4e647649ff7a460420bb5f0,
title = "Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception: Language Agents for Cyber Deception",
abstract = "This paper presents the SANDMAN architecture for cyber deception, employing Language Agents to create convincing human simulacra. These {"}Deceptive Agents{"} serve as advanced cyber decoys, designed to engage attackers to extend the observation period of attack behaviours. This research demonstrates the viability of persona-driven Deceptive Agents to generate plausible human activity to enhance the effectiveness of cyber deception strategies. Through experimentation, measurement and analysis, we illustrate how a prompt schema induces specific {"}personalities{"}, defined by the five-factor model of personality, in Large Language Models to generate measurably diverse, and plausible, behaviours.",
author = "Lewis Newsham and Daniel Prince and Ryan Hyland",
year = "2024",
month = jul,
day = "29",
language = "English",
pages = "48--58",
note = "Natural Language Processing and Artificial Intelligence for Cyber Security , NLPAICS 2024 ; Conference date: 29-07-2024 Through 30-07-2024",
url = "https://www.lancaster.ac.uk/dsi/about-us/events/natural-language-processing-and-artificial-intelligence-for-cyber-security-nlpaics-2024/",

}

RIS

TY - CONF

T1 - Measuring the Effect of Induced Persona on Agenda Creation in Language-based Agents for Cyber Deception

T2 - Natural Language Processing and Artificial Intelligence for Cyber Security

AU - Newsham, Lewis

AU - Prince, Daniel

AU - Hyland, Ryan

PY - 2024/7/29

Y1 - 2024/7/29

N2 - This paper presents the SANDMAN architecture for cyber deception, employing Language Agents to create convincing human simulacra. These "Deceptive Agents" serve as advanced cyber decoys, designed to engage attackers to extend the observation period of attack behaviours. This research demonstrates the viability of persona-driven Deceptive Agents to generate plausible human activity to enhance the effectiveness of cyber deception strategies. Through experimentation, measurement and analysis, we illustrate how a prompt schema induces specific "personalities", defined by the five-factor model of personality, in Large Language Models to generate measurably diverse, and plausible, behaviours.

AB - This paper presents the SANDMAN architecture for cyber deception, employing Language Agents to create convincing human simulacra. These "Deceptive Agents" serve as advanced cyber decoys, designed to engage attackers to extend the observation period of attack behaviours. This research demonstrates the viability of persona-driven Deceptive Agents to generate plausible human activity to enhance the effectiveness of cyber deception strategies. Through experimentation, measurement and analysis, we illustrate how a prompt schema induces specific "personalities", defined by the five-factor model of personality, in Large Language Models to generate measurably diverse, and plausible, behaviours.

M3 - Conference paper

SP - 48

EP - 58

Y2 - 29 July 2024 through 30 July 2024

ER -