Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Chatgpt for cybersecurity: practical applications, challenges, and future directions

Open access

Abstract

Artificial intelligence (AI) advancements have revolutionized many critical domains by providing cost-effective, automated, and intelligent solutions. Recently, ChatGPT has achieved a momentous change and made substantial progress in natural language processing. As such, a chatbot-driven AI technology has the capabilities to interact and communicate with users and generate human-like responses. ChatGPT, on the other hand, has the potential to influence changes in the cybersecurity domain. ChatGPT can be utilized as a chatbot-driven security assistant for penetration testing to analyze, investigate, and develop security solutions. However, ChatGPT raises concerns about how the tool can be used for cybercrime and malicious activities. Attackers can use such a tool to cause substantial harm by exploiting vulnerabilities, writing malicious code, and circumventing security measures on a targeted system. This article investigates the implications of the ChatGPT model in the domain of cybersecurity. We present the state-of-the-art practical applications of ChatGPT in cybersecurity. In addition, we demonstrate in a case study how a ChatGPT can be used to design and develop False data injection attacks against critical infrastructure such as industrial control systems. Conversely, we show how such a tool can be used to help security analysts to analyze, design, and develop security solutions against cyberattacks. Finally, this article discusses the open challenges and future directions of ChatGPT in cybersecurity.

Overview

Integrity signals

Registry

Crossref · 10.1007/s10586-023-04124-5

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 22 references

Research works printed but not linked: 14

  1. Wu, J.: Literature review on vulnerability detection using NLP technology. arXiv preprint arXiv:2104.11230 (2021) · arXiv
  2. McKee, F., Noever, D.: Chatbots in a botnet world. arXiv preprint arXiv:2212.11126 (2022) · arXiv
  3. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)
  4. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A.: Language models are few-shot learners. Adv. Neural Inform. Process. Syst. 33, 1877–1901 (2020)
  5. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A.: Training language models to follow instructions with human feedback. Adv. Neural Inform. Process. Syst. 35, 27730–27744 (2022)
  6. Noever, D., Williams, K.: Chatbots as fluent polyglots: revisiting breakthrough code snippets. arXiv preprint arXiv:2301.03373 (2023) · arXiv
  7. Karanjai, R.: Targeted phishing campaigns using large scale language models. arXiv preprint arXiv:2301.00665 (2022) · arXiv
  8. Susnjak, T.: Chatgpt: The end of online exam integrity? arXiv preprint arXiv:2212.09292 (2022) · arXiv
  9. Pang, Z.-H., Fan, L.-Z., Dong, Z., Han, Q.-L., Liu, G.-P.: False data injection attacks against partial sensor measurements of networked control systems. IEEE Trans. Circ. Syst. II: Express Briefs 69(1), 149–153 (2021)
  10. Jolfaei, A., Kant, K.: On the silent perturbation of state estimation in smart grid. IEEE Trans. Ind. Appl. 56(4), 4405–4414 (2020)
  11. Balash, D.G., Wu, X., Grant, M., Reyes, I., Aviv, A.J.: Security and privacy perceptions of $$\{$$Third-Party$$\}$$ application access for google accounts. In: 31st USENIX security symposium (USENIX Security 22), pp. 3397–3414 (2022)
  12. Roy, S.S., Naragam, K.V., Nilizadeh, S.: Generating phishing attacks using chatgpt. arXiv preprint arXiv:2305.05133 (2023) · arXiv
  13. Renaud, K., Warkentin, M., Westerman, G.: From ChatGPT to HackGPT: Meeting the cybersecurity threat of generative AI. MIT Sloan Management Review (2023)
  14. Sebastian, G.: Do chatgpt and other AI chatbots pose a cybersecurity risk?: an exploratory study. Int. J. Secur. Priv. Pervas. Comput. (IJSPPC) 15(1), 1–11 (2023)

Cited by

See all 124

Metadata

Authors
Al-Hawawreh, M., Aljuhani, A., & Jararweh, Y.
Affiliations
  • Deakin University (AU)
  • University of Tabuk (SA)
  • Jordan University of Science and Technology (JO)
Corresponding author
Al-Hawawreh, Muna
Venue
Cluster Computing
Published
2023-08-24
Volume
26
Issue
6
Pages
3421-3436
ISSN
  • 1386-7857 (ISSN-L)
  • 1573-7543
OpenAlex
W4386119501
Cited by
124
References
22
Citations by year
2026: 19 · 2025: 41 · 2024: 58 · 2023: 6
FWCI
10.70
Type
journal article
Language
en
Open access
Licence
Locations
  • Cluster Computing (publishedVersion)
  • Figshare (submittedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
  • Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
Keywords
ChatGPT, cybersecurity applications, chatbots, penetration testing, false data injection attacks, industrial control systems, critical infrastructure security, cybercrime, large language models

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Chatgpt for cybersecurity: practical applications, challenges, and future directions. https://app.cochat.ai/papers/10.1007/s10586-023-04124-5
The paper
Al-Hawawreh, M., Aljuhani, A., & Jararweh, Y. (2023). Chatgpt for cybersecurity: practical applications, challenges, and future directions. Cluster Computing. https://doi.org/10.1007/s10586-023-04124-5

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.