Review article · 2026 · Open access

A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities

Jaqueline Damacena Duarte, Guilherme Dieguez Candido, José Ricardo A. De Britto Filho, João Souza Neto, Elena J. da Costa, João Paulo J. Da Costa, Laerte Peotta de Melo

IEEE Access, 14, 12875–12899 · Published 1 January 2026 · DOI 10.1109/access.2026.3656849

Open full textCite this paper

In brief

“A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities” is a 2026 review article by Jaqueline Damacena Duarte and 6 co-authors, published in IEEE Access. OpenAlex counts 34 citations as of 17 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE Access.

Citations
34
Most cited in
2026 (33)
Field-weighted impact
11.66
References
92
Authors
7

Abstract

Large Language Models (LLMs) are increasingly integrated into various infrastructure and interactive applications. However, their inherent linguistic flexibility introduces security vulnerabilities, particularly through Prompt Injection (PI) attacks. This systematic review provides a comprehensive synthesis of the evolving landscape of PI attacks, including their development trends, classification schemes, evaluation methodologies, defense strategies, and areas for future research. We analyze the evolution of attacks from basic natural language overrides to complex multi-turn manipulations, indirect injections using structured formats such as JSON and XML, and tool-assisted exploits involving automated prompt generation and multi-modal inputs like images. PI attacks are categorized by the level of manipulation, including character, word, sentence, and semantic levels, and by adversarial intent, such as prompt leaking and harmful content generation. The study analyzes these techniques within different LLM architectures and application contexts, including machine translation and Chain of Thought reasoning. It also reviews common evaluation benchmarks, datasets, and metrics. Mitigation strategies examined include automated red teaming frameworks, input validation, content filtering, and alignment through training. It differentiates itself from previous works by conducting a systematic review specifically focused on immediate injection, organizing its attacks, defenses and research gaps. Finally, this review identifies major research challenges and suggests critical directions for improving LLM safety and robustness.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Duarte, J. D., Candido, G. D., Filho, J. R. A. D. B., Neto, J. S., da Costa, E. J., Da Costa, J. P. J., & de Melo, L. P. (2026). A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities. IEEE Access, 14, 12875–12899. https://doi.org/10.1109/access.2026.3656849

MLA 9

Duarte, Jaqueline Damacena, et al. “A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities.” IEEE Access, vol. 14, 2026, pp. 12875–12899. https://doi.org/10.1109/access.2026.3656849.

Chicago

Duarte, Jaqueline Damacena, Guilherme Dieguez Candido, José Ricardo A. De Britto Filho, João Souza Neto, Elena J. da Costa, João Paulo J. Da Costa, and Laerte Peotta de Melo. 2026. “A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities.” IEEE Access 14: 12875–12899. https://doi.org/10.1109/access.2026.3656849.

Harvard

Duarte, J. D. et al. (2026) ‘A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities’, IEEE Access, 14, pp. 12875–12899. doi:10.1109/access.2026.3656849.

IEEE

J. D. Duarte et al., “A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities,” IEEE Access, vol. 14, pp. 12875–12899, 2026, doi: 10.1109/access.2026.3656849.

BibTeX

@article{duarte2026systematic,
  title     = {{A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities}},
  author    = {Duarte, Jaqueline Damacena and Candido, Guilherme Dieguez and Filho, José Ricardo A. De Britto and Neto, João Souza and da Costa, Elena J. and Da Costa, João Paulo J. and de Melo, Laerte Peotta},
  journal   = {IEEE Access},
  year      = {2026},
  volume    = {14},
  pages     = {12875--12899},
  doi       = {10.1109/access.2026.3656849},
  url       = {https://doi.org/10.1109/access.2026.3656849}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • prompt injection
  • large language models
  • LLM security
  • attack taxonomy
  • harmful content generation
  • defense strategy
  • input validation
  • content filtering

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Duarte, J. D., Candido, G. D., Filho, J. R. A. D. B., Neto, J. S., da Costa, E. J., Da Costa, J. P. J., & de Melo, L. P. (2026). A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities. IEEE Access, 14, 12875–12899. https://doi.org/10.1109/access.2026.3656849

How many times has this paper been cited?

34 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Access: sign in and open the full text from this page.

Who wrote this paper?

Jaqueline Damacena Duarte, Guilherme Dieguez Candido, José Ricardo A. De Britto Filho, João Souza Neto, Elena J. da Costa, João Paulo J. Da Costa, Laerte Peotta de Melo.

What is the DOI of this paper?

10.1109/access.2026.3656849, permanently at https://doi.org/10.1109/access.2026.3656849. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.