Preprint · 2026 · Open access
Loose Lips: Understanding Privacy Leakage in Agentic Dialogue
arXiv (Cornell University) · Published 7 October 2026 · DOI 10.48550/arxiv.2610.14071
In brief
“Loose Lips: Understanding Privacy Leakage in Agentic Dialogue” is a 2026 preprint by Soumya Sharma and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 22
- Authors
- 7
Abstract
As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue has become critical. Privacy leakage in such settings requires reasoning about whether information flows respect the contextual norms under which they originated. We extend CIMemories to CIMEMORIES DIALOGUE, a benchmark of 4,410 two-agent dialogue instances grounded in Contextual Integrity theory. Using this benchmark, we systematically evaluate 7 open-weight models from the Qwen3 and Llama 3.1 families across conversation lengths of 1 and 6 turns under three prompting conditions. We find that task capability and privacy leakage are fundamentally coupled: more capable models are systematically leakier, with no model in our evaluation able to decouple the two. Thinking models consistently leak more than their non-thinking counterparts, a pattern we attribute to the extended reasoning surface created by chain-of-thought. Leakage compounds with conversation length, rising up to 3x from 1 to 6 turns. Our results suggest that the coupling between task capability and privacy leakage is not an artifact of misconfiguration but a structural feature of current agentic systems.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Sharma, S., Hussain, A., Arcolezi, H. H., Aïvodji, U., Gella, S., Romero, A., & Farnadi, G. (2026). Loose Lips: Understanding Privacy Leakage in Agentic Dialogue. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.14071
MLA 9
Sharma, Soumya, et al. “Loose Lips: Understanding Privacy Leakage in Agentic Dialogue.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.14071.
Chicago
Sharma, Soumya, Ayana Hussain, Héber H. Arcolezi, Ulrich Aïvodji, Spandana Gella, Adriana Romero, and Golnoosh Farnadi. 2026. “Loose Lips: Understanding Privacy Leakage in Agentic Dialogue.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.14071.
Harvard
Sharma, S. et al. (2026) ‘Loose Lips: Understanding Privacy Leakage in Agentic Dialogue’, arXiv (Cornell University). doi:10.48550/arxiv.2610.14071.
IEEE
S. Sharma et al., “Loose Lips: Understanding Privacy Leakage in Agentic Dialogue,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.14071.
BibTeX
@misc{sharma2026loose,
title = {{Loose Lips: Understanding Privacy Leakage in Agentic Dialogue}},
author = {Sharma, Soumya and Hussain, Ayana and Arcolezi, Héber H. and Aïvodji, Ulrich and Gella, Spandana and Romero, Adriana and Farnadi, Golnoosh},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2610.14071},
url = {https://doi.org/10.48550/arxiv.2610.14071}
}
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
- privacy leakage
- LLM agents
- contextual integrity
- chain-of-thought prompting
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?
Sharma, S., Hussain, A., Arcolezi, H. H., Aïvodji, U., Gella, S., Romero, A., & Farnadi, G. (2026). Loose Lips: Understanding Privacy Leakage in Agentic Dialogue. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.14071
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?
Soumya Sharma, Ayana Hussain, Héber H. Arcolezi, Ulrich Aïvodji, Spandana Gella, Adriana Romero, Golnoosh Farnadi.
What is the DOI of this paper?
10.48550/arxiv.2610.14071, permanently at https://doi.org/10.48550/arxiv.2610.14071. 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.