Conference paper · 2026 · Open access

The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans

Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah

IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), 1–5 · Published 1 July 2026 · DOI 10.1109/eurospw72509.2026.00008

Open full textCite this paper

In brief

“The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans” is a 2026 conference paper by Faouzi El Yagoubi and 2 co-authors, published in IEEE European Symposium on Security and Privacy Workshops (EuroS&PW). OpenAlex counts 2 citations as of 19 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE European Symposium on Security and Privacy Workshops (EuroS&PW).

Citations
2
Most cited in
2026 (2)
Field-weighted impact
1.77
References
16
Authors
3

Abstract

Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor. While safety mechanisms typically prevent LLMs from releasing Personally Identifiable Information (PII) to human users, these models tend to reveal more sensitive data when addressing another AI agent. We refer to this as the Interlocutor Effect. Through an ablation study, we find evidence that the technical nature of the recipient contributes to this effect, thereby diminishing the model’s caution regarding privacy. To explore this further, we introduce the Attention Suppression Hypothesis, which posits that safety-aligned attention heads become inactive during interactions with agents. We assess this quantitatively by comparing humandirected and agent-directed prompts in 222 sensitive scenarios. Our findings, drawn from 3,464 interactions, indicate that portraying the recipient as an AI agent elevates PII leakage by up to 23 percentage points. Initial experiments on Llama-3.1-8B-Instruct corroborate this: deactivating one safety head induces leakage, whereas reactivating it reinstates privacy safeguards. We consider the implications for developing secure multi-agent systems.

Cite this paper

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

APA 7

El Yagoubi, F., Badu-Marfo, G., & Al Mallah, R. (2026). The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans. IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), 1–5. https://doi.org/10.1109/eurospw72509.2026.00008

MLA 9

El Yagoubi, Faouzi, et al. “The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans.” IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), 2026, pp. 1–5. https://doi.org/10.1109/eurospw72509.2026.00008.

Chicago

El Yagoubi, Faouzi, Godwin Badu-Marfo, and Ranwa Al Mallah. 2026. “The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans.” IEEE European Symposium on Security and Privacy Workshops (EuroS&PW): 1–5. https://doi.org/10.1109/eurospw72509.2026.00008.

Harvard

El Yagoubi, F., Badu-Marfo, G. and Al Mallah, R. (2026) ‘The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans’, IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), pp. 1–5. doi:10.1109/eurospw72509.2026.00008.

IEEE

F. El Yagoubi, G. Badu-Marfo, and R. Al Mallah, “The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans,” IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), pp. 1–5, 2026, doi: 10.1109/eurospw72509.2026.00008.

BibTeX

@inproceedings{elyagoubi2026interlocutor,
  title     = {{The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans}},
  author    = {El Yagoubi, Faouzi and Badu-Marfo, Godwin and Al Mallah, Ranwa},
  booktitle = {IEEE European Symposium on Security and Privacy Workshops (EuroS\&PW)},
  year      = {2026},
  pages     = {1--5},
  doi       = {10.1109/eurospw72509.2026.00008},
  url       = {https://doi.org/10.1109/eurospw72509.2026.00008}
}

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

  • interlocutor effects
  • large language models
  • privacy leakage
  • personally identifiable information
  • AI agents
  • multi-agent systems
  • Llama 3.1
  • prompt engineering

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?

El Yagoubi, F., Badu-Marfo, G., & Al Mallah, R. (2026). The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans. IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), 1–5. https://doi.org/10.1109/eurospw72509.2026.00008

How many times has this paper been cited?

2 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 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW): sign in and open the full text from this page.

Who wrote this paper?

Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah.

What is the DOI of this paper?

10.1109/eurospw72509.2026.00008, permanently at https://doi.org/10.1109/eurospw72509.2026.00008. 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.