Journal article · 2026 · Open access
AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems
IEEE Access, 14, 94960–94978 · Published 1 January 2026 · DOI 10.1109/access.2026.3704541
In brief
“AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems” is a 2026 journal article by Faouzi El Yagoubi and 2 co-authors, published in IEEE Access. OpenAlex counts 105 citations as of 17 November 2026, which puts it in the top 1% 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 Access.
- Citations
- 105
- Most cited in
- 2026 (105)
- Field-weighted impact
- 115.80
- References
- 34
- Authors
- 3
Abstract
Multi-agent Large Language Model (LLM) systems create privacy risks that current output-only benchmarks cannot measure. When agents coordinate on tasks, sensitive data may pass through inter-agent messages, shared memory, and tool arguments, all pathways that final-output audits typically do not inspect. We introduce AgentLeak, a benchmark for evaluating internal-channel privacy leakage in multi-agent LLM systems. AgentLeak instruments seven privacy-relevant communication pathways and provides a large-scale empirical evaluation focused on final outputs, inter-agent messages, and shared memory. Across 1,000 scenarios spanning healthcare, finance, legal, and corporate domains, five production LLMs (GPT-4o, GPT-4o-mini, Claude 3.5 Sonnet, Mistral Large, and Llama 3.3 70B), and 4,979 validated execution traces, we find that multi-agent configurations reduce final-output leakage (C1: 27.2% vs 43.2% in single-agent mode) compared with single-agent baselines but introduce internal channels that raise total system exposure to 68.9% (aggregated across C1, C2, C5). Inter-agent messages (C2) leak at 68.8%, compared with 27.2% for final outputs (C1), meaning that output-only audits miss 41.7% of violations. Across all five models and four domains, the pattern C2 $\geq$ C1 holds consistently. These results suggest, within the evaluated coordinator-worker setting, that privacy risk in multi-agent systems is strongly shaped by architectural coordination channels rather than final-output behavior alone: it arises from internal channels that remain invisible to standard output-level defenses.
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). AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems. IEEE Access, 14, 94960–94978. https://doi.org/10.1109/access.2026.3704541
MLA 9
El Yagoubi, Faouzi, et al. “AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems.” IEEE Access, vol. 14, 2026, pp. 94960–94978. https://doi.org/10.1109/access.2026.3704541.
Chicago
El Yagoubi, Faouzi, Godwin Badu-Marfo, and Ranwa Al Mallah. 2026. “AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems.” IEEE Access 14: 94960–94978. https://doi.org/10.1109/access.2026.3704541.
Harvard
El Yagoubi, F., Badu-Marfo, G. and Al Mallah, R. (2026) ‘AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems’, IEEE Access, 14, pp. 94960–94978. doi:10.1109/access.2026.3704541.
IEEE
F. El Yagoubi, G. Badu-Marfo, and R. Al Mallah, “AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems,” IEEE Access, vol. 14, pp. 94960–94978, 2026, doi: 10.1109/access.2026.3704541.
BibTeX
@article{elyagoubi2026agentleak,
title = {{AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems}},
author = {El Yagoubi, Faouzi and Badu-Marfo, Godwin and Al Mallah, Ranwa},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {94960--94978},
doi = {10.1109/access.2026.3704541},
url = {https://doi.org/10.1109/access.2026.3704541}
}
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
- multi-agent large language models
- privacy leakage
- shared memory
- privacy auditing
- LLM security
- execution traces
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?
El Yagoubi, F., Badu-Marfo, G., & Al Mallah, R. (2026). AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems. IEEE Access, 14, 94960–94978. https://doi.org/10.1109/access.2026.3704541
How many times has this paper been cited?
105 times, according to OpenAlex on 17 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 Access: 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/access.2026.3704541, permanently at https://doi.org/10.1109/access.2026.3704541. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 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.