Journal article · 2025

Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey

Yaxin Tang, Yijia Liu, Jiahe Lan, Zheng Yan, Erol Gelenbe

Information Fusion, 127, 103941 · Published 12 November 2025 · DOI 10.1016/j.inffus.2025.103941

View at the publisherCite this paper

In brief

“Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey” is a 2025 journal article by Yaxin Tang and 4 co-authors, published in Information Fusion. OpenAlex counts 43 citations as of 19 November 2026, which puts it in the top 1% of works published in 2025 by citations. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
43
Most cited in
2026 (43)
Field-weighted impact
8.06
References
176
Authors
5

Cite this paper

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

APA 7

Tang, Y., Liu, Y., Lan, J., Yan, Z., & Gelenbe, E. (2025). Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey. Information Fusion, 127, 103941. https://doi.org/10.1016/j.inffus.2025.103941

MLA 9

Tang, Yaxin, et al. “Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey.” Information Fusion, vol. 127, 2025, p. 103941. https://doi.org/10.1016/j.inffus.2025.103941.

Chicago

Tang, Yaxin, Yijia Liu, Jiahe Lan, Zheng Yan, and Erol Gelenbe. 2025. “Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey.” Information Fusion 127: 103941. https://doi.org/10.1016/j.inffus.2025.103941.

Harvard

Tang, Y. et al. (2025) ‘Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey’, Information Fusion, 127, p. 103941. doi:10.1016/j.inffus.2025.103941.

IEEE

Y. Tang, Y. Liu, J. Lan, Z. Yan, and E. Gelenbe, “Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey,” Information Fusion, vol. 127, p. 103941, 2025, doi: 10.1016/j.inffus.2025.103941.

BibTeX

@article{tang2025security,
  title     = {{Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey}},
  author    = {Tang, Yaxin and Liu, Yijia and Lan, Jiahe and Yan, Zheng and Gelenbe, Erol},
  journal   = {Information Fusion},
  year      = {2025},
  volume    = {127},
  pages     = {103941},
  doi       = {10.1016/j.inffus.2025.103941},
  url       = {https://doi.org/10.1016/j.inffus.2025.103941}
}

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

  • LLM agents
  • large language models
  • security attacks
  • security defenses
  • cybercrime
  • cyber defense
  • attack surface
  • multi-stage planning

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?

Tang, Y., Liu, Y., Lan, J., Yan, Z., & Gelenbe, E. (2025). Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey. Information Fusion, 127, 103941. https://doi.org/10.1016/j.inffus.2025.103941

How many times has this paper been cited?

43 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?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Yaxin Tang, Yijia Liu, Jiahe Lan, Zheng Yan, Erol Gelenbe.

What is the DOI of this paper?

10.1016/j.inffus.2025.103941, permanently at https://doi.org/10.1016/j.inffus.2025.103941. 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.