Preprint · 2026 · Open access
CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
arXiv (Cornell University) · Published 18 September 2026 · DOI 10.48550/arxiv.2609.21686
In brief
“CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents” is a 2026 preprint by Tao Huang and 7 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
- 17
- Authors
- 8
Abstract
Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval, or tool-use pipelines, which makes it difficult to distinguish internal exposure from information that an external observer can actually recover. We present CIPL (Channel Inversion for Privacy Leakage), a channel-aware evaluation framework for black-box privacy leakage in LLM agents. CIPL represents a target through sensitive source, selection, assembly, execution, observation, and extraction stages and evaluates the transition from selected sensitive units to attacker-recoverable output under a shared protocol. Experiments across memory-based, retrieval-mediated, and tool-mediated targets, together with a BrowserUse live-agent case study, show that storage labels alone do not determine recoverability. Memory targets form a near-saturated reference case, retrieval-mediated leakage is frequently partial, and tool-mediated and live-agent leakage varies strongly with observation surface, prompt-to-channel alignment, retrieval depth, and provider behavior. A stratified semantic audit further identifies attacker-useful disclosures that canonical exact matching misses. CIPL therefore provides a common framework for comparing how internal sensitive dependence is realized as externally recoverable leakage across heterogeneous agent pipelines.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Huang, T., Wu, G., Zheng, G., Meng, J., Hou, C., Yang, X., Yang, X., & Xia, F. (2026). CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.21686
MLA 9
Huang, Tao, et al. “CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.21686.
Chicago
Huang, Tao, Guosen Wu, Guolong Zheng, Jiayang Meng, Chen Hou, Xu Yang, Xuechao Yang, and Feng Xia. 2026. “CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.21686.
Harvard
Huang, T. et al. (2026) ‘CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2609.21686.
IEEE
T. Huang et al., “CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.21686.
BibTeX
@misc{huang2026cipl,
title = {{CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents}},
author = {Huang, Tao and Wu, Guosen and Zheng, Guolong and Meng, Jiayang and Hou, Chen and Yang, Xu and Yang, Xuechao and Xia, Feng},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2609.21686},
url = {https://doi.org/10.48550/arxiv.2609.21686}
}
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
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?
Huang, T., Wu, G., Zheng, G., Meng, J., Hou, C., Yang, X., Yang, X., & Xia, F. (2026). CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.21686
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?
Tao Huang, Guosen Wu, Guolong Zheng, Jiayang Meng, Chen Hou, Xu Yang, Xuechao Yang, Feng Xia.
What is the DOI of this paper?
10.48550/arxiv.2609.21686, permanently at https://doi.org/10.48550/arxiv.2609.21686. 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.