Preprint · 2025 · Open access

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents

Saswat Das, Jameson Sandler, Ferdinando Fioretto

arXiv (Cornell University) · Published 11 June 2025 · DOI 10.48550/arxiv.2506.10171

Open PDFView at the publisherCite this paper

In brief

“Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents” is a 2025 preprint by Saswat Das and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 12 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
12
Most cited in
2026 (10)
References
15
Authors
3

Abstract

LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also require continuous access to sensitive data, which increases the likelihood of unauthorized disclosures. Moreover, these disclosures go beyond mere explicit disclosure, leaving open avenues for gradual manipulation or sidechannel information leakage. This study proposes an auditing framework for conversational privacy that quantifies an agent's susceptibility to these risks. The proposed Conversational Manipulation for Privacy Leakage (CMPL) framework is designed to stress-test agents that enforce strict privacy directives against an iterative probing strategy. Rather than focusing solely on a single disclosure event or purely explicit leakage, CMPL simulates realistic multi-turn interactions to systematically uncover latent vulnerabilities. Our evaluation on diverse domains, data modalities, and safety configurations demonstrates the auditing framework's ability to reveal privacy risks that are not deterred by existing single-turn defenses, along with an in-depth longitudinal study of the temporal dynamics of leakage, strategies adopted by adaptive adversaries, and the evolution of adversarial beliefs about sensitive targets. In addition to introducing CMPL as a diagnostic tool, the paper delivers (1) an auditing procedure grounded in quantifiable risk metrics and (2) an open benchmark for evaluation of conversational privacy across agent implementations.

Cite this paper

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

APA 7

Das, S., Sandler, J., & Fioretto, F. (2025). Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.10171

MLA 9

Das, Saswat, et al. “Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2506.10171.

Chicago

Das, Saswat, Jameson Sandler, and Ferdinando Fioretto. 2025. “Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.10171.

Harvard

Das, S., Sandler, J. and Fioretto, F. (2025) ‘Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2506.10171.

IEEE

S. Das, J. Sandler, and F. Fioretto, “Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2506.10171.

BibTeX

@misc{das2025beyond,
  title     = {{Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents}},
  author    = {Das, Saswat and Sandler, Jameson and Fioretto, Ferdinando},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2506.10171},
  url       = {https://doi.org/10.48550/arxiv.2506.10171}
}

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
  • multi-turn interaction
  • sensitive information disclosure
  • jailbreaking

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?

Das, S., Sandler, J., & Fioretto, F. (2025). Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.10171

How many times has this paper been cited?

12 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?

Saswat Das, Jameson Sandler, Ferdinando Fioretto.

What is the DOI of this paper?

10.48550/arxiv.2506.10171, permanently at https://doi.org/10.48550/arxiv.2506.10171. 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.