Personality Emulation Utilizing Large Language Models

Fake identities have proven to be an effective methodology for conducting privacy and cybersecurity research; however, existing models are limited in their ability to interact with and respond to received communications. To perform privacy research in more complex Internet domains, withstand enhance...

Full description

Saved in:
Bibliographic Details
Main Authors: Jack Kolenbrander, Alan J. Michaels
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/12/6636
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433619018285056
author Jack Kolenbrander
Alan J. Michaels
author_facet Jack Kolenbrander
Alan J. Michaels
author_sort Jack Kolenbrander
collection DOAJ
description Fake identities have proven to be an effective methodology for conducting privacy and cybersecurity research; however, existing models are limited in their ability to interact with and respond to received communications. To perform privacy research in more complex Internet domains, withstand enhanced scrutiny, and persist long-term, fake identities must be capable of automatically generating responses while maintaining consistent behavior and personality. This work proposes a method for assigning personality to fake identities using the widely accepted psychometric Big Five model. Leveraging this model, the potential application of large language models (LLMs) to generate email responses that emulate human personality traits is investigated to enhance fake identity capabilities for privacy research at scale.
format Article
id doaj-art-4f2b980374ca41dfac53163c718170f7
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-4f2b980374ca41dfac53163c718170f72025-08-20T03:26:57ZengMDPI AGApplied Sciences2076-34172025-06-011512663610.3390/app15126636Personality Emulation Utilizing Large Language ModelsJack Kolenbrander0Alan J. Michaels1Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USABradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USAFake identities have proven to be an effective methodology for conducting privacy and cybersecurity research; however, existing models are limited in their ability to interact with and respond to received communications. To perform privacy research in more complex Internet domains, withstand enhanced scrutiny, and persist long-term, fake identities must be capable of automatically generating responses while maintaining consistent behavior and personality. This work proposes a method for assigning personality to fake identities using the widely accepted psychometric Big Five model. Leveraging this model, the potential application of large language models (LLMs) to generate email responses that emulate human personality traits is investigated to enhance fake identity capabilities for privacy research at scale.https://www.mdpi.com/2076-3417/15/12/6636large language modelsfake identitiesprivacy researchactive OSINTbig five personality modelartificial intelligence
spellingShingle Jack Kolenbrander
Alan J. Michaels
Personality Emulation Utilizing Large Language Models
Applied Sciences
large language models
fake identities
privacy research
active OSINT
big five personality model
artificial intelligence
title Personality Emulation Utilizing Large Language Models
title_full Personality Emulation Utilizing Large Language Models
title_fullStr Personality Emulation Utilizing Large Language Models
title_full_unstemmed Personality Emulation Utilizing Large Language Models
title_short Personality Emulation Utilizing Large Language Models
title_sort personality emulation utilizing large language models
topic large language models
fake identities
privacy research
active OSINT
big five personality model
artificial intelligence
url https://www.mdpi.com/2076-3417/15/12/6636
work_keys_str_mv AT jackkolenbrander personalityemulationutilizinglargelanguagemodels
AT alanjmichaels personalityemulationutilizinglargelanguagemodels