Automatic scam-baiting using ChatGPT

Piyush Bajaj; Matthew  Edwards

doi:10.1109/TrustCom60117.2023.00264

Automatic scam-baiting using ChatGPT

Piyush Bajaj^*, Matthew Edwards

^*Corresponding author for this work

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

20 Downloads (Pure)

Abstract

Automatic scam-baiting is an online fraud countermeasure that involves automated systems responding to online fraudsters in order to waste their time and deplete their resources, diverting attackers away from real potential victims. Previous work has demonstrated that text generation systems are capable of engaging with attackers as automatic scam-baiters, but the fluency and coherence of generated text may be a limit to the effectiveness of such systems.

In this paper, we report on the results of a month-long experiment comparing the effectiveness of two ChatGPT-based automatic scam-baiters to a control measure. Within our results, with engagement from over 250 real email fraudsters, we find that ChatGPT-based scam-baiters show a marked increase in scammer response rate and conversation length relative to the control measure, outperforming previous approaches. We discuss the implications of these results and practical considerations for wider deployment of automatic scam-baiting.

Original language	English
Title of host publication	Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023)
Editors	Jia Hu, Geyong Min, Guojun Wang
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1941-1946
Number of pages	6
ISBN (Electronic)	9798350381993
DOIs	https://doi.org/10.1109/TrustCom60117.2023.00264
Publication status	Published - 29 May 2024
Event	The 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics - Exeter, United Kingdom Duration: 1 Nov 2023 → 3 Nov 2023

Publication series

Name	International Conference on Trust, Security and Privacy in Computing and Communications
Publisher	IEEE
ISSN (Print)	2324-898X
ISSN (Electronic)	2324-9013

Conference

Conference	The 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics
Abbreviated title	ACE-2023
Country/Territory	United Kingdom
City	Exeter
Period	1/11/23 → 3/11/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Structured keywords

Cyber Security

Access to Document

10.1109/TrustCom60117.2023.00264Licence: Unspecified

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (Version of Record) can be found on the publisher's website. The copyright of any third-party content, such as images, remains with the copyright holder.
Accepted author manuscript, 210 KBLicence: CC BY

Handle.net

Persistent link

Cite this

Bajaj, P., & Edwards, M. (2024). Automatic scam-baiting using ChatGPT. In J. Hu, G. Min, & G. Wang (Eds.), Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023) (pp. 1941-1946). (International Conference on Trust, Security and Privacy in Computing and Communications). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/TrustCom60117.2023.00264

Bajaj, Piyush ; Edwards, Matthew . / Automatic scam-baiting using ChatGPT. Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023). editor / Jia Hu ; Geyong Min ; Guojun Wang. Institute of Electrical and Electronics Engineers (IEEE), 2024. pp. 1941-1946 (International Conference on Trust, Security and Privacy in Computing and Communications).

@inproceedings{21bbb8b40ef64dcf9256b331fc38858c,

title = "Automatic scam-baiting using ChatGPT",

abstract = "Automatic scam-baiting is an online fraud countermeasure that involves automated systems responding to online fraudsters in order to waste their time and deplete their resources, diverting attackers away from real potential victims. Previous work has demonstrated that text generation systems are capable of engaging with attackers as automatic scam-baiters, but the fluency and coherence of generated text may be a limit to the effectiveness of such systems. In this paper, we report on the results of a month-long experiment comparing the effectiveness of two ChatGPT-based automatic scam-baiters to a control measure. Within our results, with engagement from over 250 real email fraudsters, we find that ChatGPT-based scam-baiters show a marked increase in scammer response rate and conversation length relative to the control measure, outperforming previous approaches. We discuss the implications of these results and practical considerations for wider deployment of automatic scam-baiting.",

author = "Piyush Bajaj and Matthew Edwards",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; The 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics , ACE-2023 ; Conference date: 01-11-2023 Through 03-11-2023",

year = "2024",

month = may,

day = "29",

doi = "10.1109/TrustCom60117.2023.00264",

language = "English",

series = "International Conference on Trust, Security and Privacy in Computing and Communications",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1941--1946",

editor = "Jia Hu and Geyong Min and Guojun Wang",

booktitle = "Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023)",

address = "United States",

}

Bajaj, P & Edwards, M 2024, Automatic scam-baiting using ChatGPT. in J Hu, G Min & G Wang (eds), Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023). International Conference on Trust, Security and Privacy in Computing and Communications, Institute of Electrical and Electronics Engineers (IEEE), pp. 1941-1946, The 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics , Exeter, United Kingdom, 1/11/23. https://doi.org/10.1109/TrustCom60117.2023.00264

Automatic scam-baiting using ChatGPT. / Bajaj, Piyush; Edwards, Matthew .
Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023). ed. / Jia Hu; Geyong Min; Guojun Wang. Institute of Electrical and Electronics Engineers (IEEE), 2024. p. 1941-1946 (International Conference on Trust, Security and Privacy in Computing and Communications).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Automatic scam-baiting using ChatGPT

AU - Bajaj, Piyush

AU - Edwards, Matthew

PY - 2024/5/29

Y1 - 2024/5/29

N2 - Automatic scam-baiting is an online fraud countermeasure that involves automated systems responding to online fraudsters in order to waste their time and deplete their resources, diverting attackers away from real potential victims. Previous work has demonstrated that text generation systems are capable of engaging with attackers as automatic scam-baiters, but the fluency and coherence of generated text may be a limit to the effectiveness of such systems. In this paper, we report on the results of a month-long experiment comparing the effectiveness of two ChatGPT-based automatic scam-baiters to a control measure. Within our results, with engagement from over 250 real email fraudsters, we find that ChatGPT-based scam-baiters show a marked increase in scammer response rate and conversation length relative to the control measure, outperforming previous approaches. We discuss the implications of these results and practical considerations for wider deployment of automatic scam-baiting.

AB - Automatic scam-baiting is an online fraud countermeasure that involves automated systems responding to online fraudsters in order to waste their time and deplete their resources, diverting attackers away from real potential victims. Previous work has demonstrated that text generation systems are capable of engaging with attackers as automatic scam-baiters, but the fluency and coherence of generated text may be a limit to the effectiveness of such systems. In this paper, we report on the results of a month-long experiment comparing the effectiveness of two ChatGPT-based automatic scam-baiters to a control measure. Within our results, with engagement from over 250 real email fraudsters, we find that ChatGPT-based scam-baiters show a marked increase in scammer response rate and conversation length relative to the control measure, outperforming previous approaches. We discuss the implications of these results and practical considerations for wider deployment of automatic scam-baiting.

UR - https://ieeexplore.ieee.org/xpl/conhome/1800729/all-proceedings

U2 - 10.1109/TrustCom60117.2023.00264

DO - 10.1109/TrustCom60117.2023.00264

M3 - Conference Contribution (Conference Proceeding)

T3 - International Conference on Trust, Security and Privacy in Computing and Communications

SP - 1941

EP - 1946

BT - Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023)

A2 - Hu, Jia

A2 - Min, Geyong

A2 - Wang, Guojun

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - The 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics

Y2 - 1 November 2023 through 3 November 2023

ER -

Bajaj P, Edwards M. Automatic scam-baiting using ChatGPT. In Hu J, Min G, Wang G, editors, Proceedings of the 7th International Workshop on Applications of AI, Cyber Security and Economics Data Analytics (ACE-2023). Institute of Electrical and Electronics Engineers (IEEE). 2024. p. 1941-1946. (International Conference on Trust, Security and Privacy in Computing and Communications). doi: 10.1109/TrustCom60117.2023.00264

Automatic scam-baiting using ChatGPT

Abstract

Publication series

Conference

Bibliographical note

Structured keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this