Journal article · 2025 · Open access

A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models

Carmen De Maio, Maria Di Gisi, Giuseppe Fenza, Mariacristina Gallo, Vincenzo Loia

IEEE Access, 13, 176482–176500 · Published 1 January 2025 · DOI 10.1109/access.2025.3619764

Open full textCite this paper

In brief

“A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models” is a 2025 journal article by Carmen De Maio and 4 co-authors, published in IEEE Access. OpenAlex counts 13 citations as of 19 November 2026, which puts it in the top 8% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE Access.

Citations
13
Most cited in
2026 (11)
Field-weighted impact
2.44
References
72
Authors
5

Abstract

Large Language Models (LLMs) have become key enablers for a wide range of natural language tasks, spanning understanding, generation, and inference across various applications and industrial domains. However, their increasing adoption has brought to light numerous security and privacy vulnerabilities, some of which remain insufficiently studied. This paper aims to identify and examine underexplored vulnerabilities affecting LLMs, with particular attention to threats that remain underrepresented in current literature. The selection of vulnerabilities is guided by a systematic comparison of four major surveys, prioritizing in-depth analysis for vulnerabilities absent in at least three of these works. The methodological approach combines a targeted literature search across major academic databases with strict inclusion and exclusion criteria focused on relevance, novelty, and the selection of peer-reviewed journal and conference publications.The survey introduces a taxonomy based on the LLM lifecycle (i.e., training, inference, and deployment) through which 17 vulnerabilities are categorized and discussed. Eight emerging threats (e.g., model collapse, gradient leakage, denial-of-service, and dependency risks) receive comprehensive analysis, reflecting their growing relevance and limited prior exploration. The result is a structured taxonomy and in-depth analysis designed to guide both academic investigations and practical efforts toward the secure deployment of LLMs in real-world environments. In addition to mapping the current threat landscape, this survey highlights open challenges and outlines key directions for future research.

Cite this paper

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

APA 7

De Maio, C., Di Gisi, M., Fenza, G., Gallo, M., & Loia, V. (2025). A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models. IEEE Access, 13, 176482–176500. https://doi.org/10.1109/access.2025.3619764

MLA 9

De Maio, Carmen, et al. “A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models.” IEEE Access, vol. 13, 2025, pp. 176482–176500. https://doi.org/10.1109/access.2025.3619764.

Chicago

De Maio, Carmen, Maria Di Gisi, Giuseppe Fenza, Mariacristina Gallo, and Vincenzo Loia. 2025. “A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models.” IEEE Access 13: 176482–176500. https://doi.org/10.1109/access.2025.3619764.

Harvard

De Maio, C. et al. (2025) ‘A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models’, IEEE Access, 13, pp. 176482–176500. doi:10.1109/access.2025.3619764.

IEEE

C. De Maio, M. Di Gisi, G. Fenza, M. Gallo, and V. Loia, “A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models,” IEEE Access, vol. 13, pp. 176482–176500, 2025, doi: 10.1109/access.2025.3619764.

BibTeX

@article{demaio2025lifecycle,
  title     = {{A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models}},
  author    = {De Maio, Carmen and Di Gisi, Maria and Fenza, Giuseppe and Gallo, Mariacristina and Loia, Vincenzo},
  journal   = {IEEE Access},
  year      = {2025},
  volume    = {13},
  pages     = {176482--176500},
  doi       = {10.1109/access.2025.3619764},
  url       = {https://doi.org/10.1109/access.2025.3619764}
}

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

  • large language models
  • LLM security
  • privacy vulnerabilities
  • vulnerability taxonomy
  • model collapse
  • gradient leakage
  • denial-of-service attacks
  • dependency risk

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?

De Maio, C., Di Gisi, M., Fenza, G., Gallo, M., & Loia, V. (2025). A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models. IEEE Access, 13, 176482–176500. https://doi.org/10.1109/access.2025.3619764

How many times has this paper been cited?

13 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 IEEE Access: sign in and open the full text from this page.

Who wrote this paper?

Carmen De Maio, Maria Di Gisi, Giuseppe Fenza, Mariacristina Gallo, Vincenzo Loia.

What is the DOI of this paper?

10.1109/access.2025.3619764, permanently at https://doi.org/10.1109/access.2025.3619764. 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.