Preprint · 2026 · Open access
AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy
arXiv (Cornell University) · Published 5 October 2026 · DOI 10.48550/arxiv.2610.06454
In brief
“AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy” is a 2026 preprint by Shouju Wang and Haopeng Zhang, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 20
- Authors
- 2
Abstract
The rapid advancement of LLM agents has enabled systems to autonomously perform complex tasks through external tools, but their growing access to personal data introduces significant privacy risks. Existing benchmarks primarily evaluate LLM agent privacy through simulated trajectories and outcome-based metrics, limiting their ability to capture privacy risks arising during multi-step agent execution. In this work, we introduce AgentPrivArena, a framework for evaluating privacy risks in realistic LLM agent workflows. AgentPrivArena integrates authentic MCP tools and self-hosted services within a reproducible execution environment. We further propose trajectory-level privacy metrics that quantify unnecessary information access beyond final response leakage. Building on this framework, we introduce AgentPrivAudit, a runtime auditing approach for monitoring privacy violations during agent execution. Extensive experiments on state-of-the-art LLM agents reveal substantial privacy risks overlooked by existing evaluation paradigms, highlighting the importance of trajectory-level auditing for trustworthy agent deployment.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, S., & Zhang, H. (2026). AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.06454
MLA 9
Wang, Shouju, and Haopeng Zhang. “AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.06454.
Chicago
Wang, Shouju and Haopeng Zhang. 2026. “AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.06454.
Harvard
Wang, S. and Zhang, H. (2026) ‘AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy’, arXiv (Cornell University). doi:10.48550/arxiv.2610.06454.
IEEE
S. Wang and H. Zhang, “AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.06454.
BibTeX
@misc{wang2026agentprivarena,
title = {{AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy}},
author = {Wang, Shouju and Zhang, Haopeng},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2610.06454},
url = {https://doi.org/10.48550/arxiv.2610.06454}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- LLM agents
- privacy auditing
- personal data exposure
- runtime monitoring
- privacy violation detection
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?
Wang, S., & Zhang, H. (2026). AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.06454
How many times has this paper been cited?
0 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?
Shouju Wang, Haopeng Zhang.
What is the DOI of this paper?
10.48550/arxiv.2610.06454, permanently at https://doi.org/10.48550/arxiv.2610.06454. 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.