Journal article · 2025 · Open access

Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses

Eleena Sarah Mathew

Journal on artificial intelligence, 7(1), 347–363 · Published 1 January 2025 · DOI 10.32604/jai.2025.069841

Open PDFView at the publisherCite this paper

In brief

“Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses” is a 2025 journal article by Eleena Sarah Mathew, published in Journal on artificial intelligence. OpenAlex counts 21 citations as of 19 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Journal on artificial intelligence.

Citations
21
Most cited in
2026 (15)
Field-weighted impact
3.94
References
47
Authors
1

Abstract

This review paper explores advanced methods to prompt Large Language Models (LLMs) into generating objectionable or unintended behaviors through adversarial prompt injection attacks. We examine a series of novel projects like HOUYI, Robustly Aligned LLM (RA-LLM), StruQ, and Virtual Prompt Injection that compel LLMs to produce affirmative responses to harmful queries. Several new benchmarks, such as PromptBench, AdvBench, AttackEval, INJECAGENT, and RobustnessSuite, have been created to evaluate the performance and resilience of LLMs against these adversarial attacks. Results show significant success rates in misleading models like Vicuna-7B, LLaMA-2-7B-Chat, GPT-3.5, and GPT-4. The review highlights limitations in existing defense mechanisms and proposes future directions for enhancing LLM alignment and safety protocols, including the concept of LLM SELF DEFENSE. Our study emphasizes the need for improved robustness in LLMs, which will potentially shape the future of Artificial Intelligence (AI) driven applications and security protocols. Understanding the vulnerabilities of LLMs is crucial for developing effective defenses against adversarial prompt injection attacks. This paper proposes a systemic classification framework that discusses various types of prompt injection attacks and defenses. We also go through a broad spectrum of state-of-the-art attack methods (such as HouYi and Virtual Prompt Injection) alongside advanced defense mechanisms (like RA-LLM, StruQ, and LLM Self-Defense), providing critical insights into vulnerabilities and robustness. We also integrate and compare results from multiple recent benchmarks, including PromptBench, INJECENT, and BIPIA.

Cite this paper

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

APA 7

Mathew, E. S. (2025). Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses. Journal on artificial intelligence, 7(1), 347–363. https://doi.org/10.32604/jai.2025.069841

MLA 9

Mathew, Eleena Sarah. “Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses.” Journal on artificial intelligence, vol. 7, no. 1, 2025, pp. 347–363. https://doi.org/10.32604/jai.2025.069841.

Chicago

Mathew, Eleena Sarah. 2025. “Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses.” Journal on artificial intelligence 7 (1): 347–363. https://doi.org/10.32604/jai.2025.069841.

Harvard

Mathew, E. S. (2025) ‘Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses’, Journal on artificial intelligence, 7(1), pp. 347–363. doi:10.32604/jai.2025.069841.

IEEE

E. S. Mathew, “Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses,” Journal on artificial intelligence, vol. 7, no. 1, pp. 347–363, 2025, doi: 10.32604/jai.2025.069841.

BibTeX

@article{mathew2025enhancing,
  title     = {{Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses}},
  author    = {Mathew, Eleena Sarah},
  journal   = {Journal on artificial intelligence},
  year      = {2025},
  volume    = {7},
  number    = {1},
  pages     = {347--363},
  doi       = {10.32604/jai.2025.069841},
  url       = {https://doi.org/10.32604/jai.2025.069841}
}

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
  • adversarial attacks
  • attack defense
  • LLM alignment
  • AI safety
  • adversarial robustness

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?

Mathew, E. S. (2025). Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses. Journal on artificial intelligence, 7(1), 347–363. https://doi.org/10.32604/jai.2025.069841

How many times has this paper been cited?

21 times, according to OpenAlex on 19 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 Journal on artificial intelligence: sign in and open the PDF from this page.

Who wrote this paper?

Eleena Sarah Mathew.

What is the DOI of this paper?

10.32604/jai.2025.069841, permanently at https://doi.org/10.32604/jai.2025.069841. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.