Journal article · 2026 · Open access
Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents
ACM Transactions on Software Engineering and Methodology · Published 7 May 2026 · DOI 10.1145/3807666
In brief
“Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents” is a 2026 journal article by Yuyou Gan and 12 co-authors, published in ACM Transactions on Software Engineering and Methodology. OpenAlex counts 118 citations as of 19 November 2026, which puts it in the top 8% of works published in 2026 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 118
- Most cited in
- 2026 (75)
- Field-weighted impact
- 79.99
- References
- 303
- Authors
- 13
Abstract
Large language models (LLMs) are increasingly embedded into software engineering workflows as autonomous or semi-autonomous agents for code generation, test synthesis, tool orchestration, and end-to-end task automation. While these agentic capabilities promise substantial productivity and quality gains, they also introduce distinct security and privacy risks at the levels of artifacts, processes, and socio-technical deployment pipelines. These risks threaten the trustworthiness of LLM-powered software and complicate core engineering activities such as specification, design, verification, maintenance, and governance. This survey systematizes the threat landscape for LLM-based agents from a software engineering perspective. We propose a taxonomy organized by threat sources and their impacts across the software lifecycle, explicitly capturing cross-module and cross-stage attack surfaces (e.g., tool-use mediation, memory management, and environment interaction). We further distill six agent features grounded in information-flow and control-flow properties that shape risk exposure. We synthesize current mitigation techniques and their limitations for each feature, and conduct four case studies on web search, gaming, navigation, and software development to illustrate practical risks and failure modes. Building on these analyses, we outline research directions in data, methodology, and policy to guide the development of secure and trustworthy LLM-based agents.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Gan, Y., Yang, Y., W, Z., He, P., Zeng, R., Wang, Y., Li, Q., Zhou, C., Li, S., Wang, T., Gao, Y., Wu, Y., & Ji, S. (2026). Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3807666
MLA 9
Gan, Yuyou, et al. “Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents.” ACM Transactions on Software Engineering and Methodology, 2026. https://doi.org/10.1145/3807666.
Chicago
Gan, Yuyou, Yi Yang, Z W, Ping He, Rui Zeng, Yiming Wang, Qingming Li, et al. 2026. “Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents.” ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3807666.
Harvard
Gan, Y. et al. (2026) ‘Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents’, ACM Transactions on Software Engineering and Methodology. doi:10.1145/3807666.
IEEE
Y. Gan et al., “Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents,” ACM Transactions on Software Engineering and Methodology, 2026, doi: 10.1145/3807666.
BibTeX
@article{gan2026navigating,
title = {{Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents}},
author = {Gan, Yuyou and Yang, Yi and W, Z and He, Ping and Zeng, Rui and Wang, Yiming and Li, Qingming and Zhou, Chunyi and Li, Songze and Wang, Ting and Gao, Yunjun and Wu, Yingcai and Ji, Shouling},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
doi = {10.1145/3807666},
url = {https://doi.org/10.1145/3807666}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 2 | |
| 2025 | 41 | |
| 2026 | 75 |
Its field-weighted citation impact is 79.99: it has been cited 79.99 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- large language models
- LLM agents
- security threats
- privacy risks
- threat taxonomy
- software lifecycle
- attack surface
- memory management
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Gan, Y., Yang, Y., W, Z., He, P., Zeng, R., Wang, Y., Li, Q., Zhou, C., Li, S., Wang, T., Gao, Y., Wu, Y., & Ji, S. (2026). Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3807666
How many times has this paper been cited?
118 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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Yuyou Gan, Yi Yang, Z W, Ping He, Rui Zeng, Yiming Wang, Qingming Li, Chunyi Zhou, Songze Li, Ting Wang, Yunjun Gao, Yingcai Wu and 1 more.
What is the DOI of this paper?
10.1145/3807666, permanently at https://doi.org/10.1145/3807666. 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.