Journal article · 2026 · Open access
Selective semantic state editing for private edge-cloud inference in SLMs
Journal of Cloud Computing Advances Systems and Applications, 15(1) · Published 22 June 2026 · DOI 10.1186/s13677-026-00939-w
In brief
“Selective semantic state editing for private edge-cloud inference in SLMs” is a 2026 journal article by Feifan Wang and 9 co-authors, published in Journal of Cloud Computing Advances Systems and Applications. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of Cloud Computing Advances Systems and Applications.
- Citations
- 0
- References
- 32
- Authors
- 10
Abstract
Edge-cloud collaborative inference in small language models offloads intermediate latent representations to bypass on-device computational bottlenecks. However, this transparent transmission exposes sensitive user attributes to latent-space inference attacks. In this paper, to effectively protect latent states during transmission, we propose Selective Semantic State Editing (SSSE), an inference-time privacy mechanism that intervenes exclusively at the offload boundary. Our framework first employs a learnable risk scorer to identify privacy-sensitive token-level latent states, then constructs on-device semantic alternatives by combining an input-conditioned local reservoir with a static prototype cache, and finally performs risk-aware selective latent state editing to suppress sensitive-attribute leakage while preserving task-relevant information. Experimental results show that SSSE provides a favorable privacy–utility balance. On the topic classification task, SSSE achieves an accuracy of 0.4691 and a macro-F1 of 0.1890, incurring only a 0.0030 macro-F1 drop from baseline. Meanwhile, SSSE reduces attack macro-F1 from 0.6539 to 0.6288 on gender, and from 0.5403 to 0.5053 on age-group. The ablation results further verify the effectiveness of the risk scorer and candidate construction. Deployment overhead study finds that SSSE introduces a practical privacy-intervention overhead of approximately 2.8 ms/sample. Our work demonstrates the practical potential of selective semantic state editing for privacy-preserving edge-cloud inference.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, F., Li, D., Ma, B., Wang, X., Li, C., Qi, X., Zhang, Y., Sha, K., Chen, H., & Yu, G. (2026). Selective semantic state editing for private edge-cloud inference in SLMs. Journal of Cloud Computing Advances Systems and Applications, 15(1). https://doi.org/10.1186/s13677-026-00939-w
MLA 9
Wang, Feifan, et al. “Selective semantic state editing for private edge-cloud inference in SLMs.” Journal of Cloud Computing Advances Systems and Applications, vol. 15, no. 1, 2026. https://doi.org/10.1186/s13677-026-00939-w.
Chicago
Wang, Feifan, Delong Li, Baihe Ma, Xu Wang, Chen Li, Xuelei Qi, Yang Zhang, Kewei Sha, Haihua Chen, and Guangsheng Yu. 2026. “Selective semantic state editing for private edge-cloud inference in SLMs.” Journal of Cloud Computing Advances Systems and Applications 15 (1). https://doi.org/10.1186/s13677-026-00939-w.
Harvard
Wang, F. et al. (2026) ‘Selective semantic state editing for private edge-cloud inference in SLMs’, Journal of Cloud Computing Advances Systems and Applications, 15(1). doi:10.1186/s13677-026-00939-w.
IEEE
F. Wang et al., “Selective semantic state editing for private edge-cloud inference in SLMs,” Journal of Cloud Computing Advances Systems and Applications, vol. 15, no. 1, 2026, doi: 10.1186/s13677-026-00939-w.
BibTeX
@article{wang2026selective,
title = {{Selective semantic state editing for private edge-cloud inference in SLMs}},
author = {Wang, Feifan and Li, Delong and Ma, Baihe and Wang, Xu and Li, Chen and Qi, Xuelei and Zhang, Yang and Sha, Kewei and Chen, Haihua and Yu, Guangsheng},
journal = {Journal of Cloud Computing Advances Systems and Applications},
year = {2026},
volume = {15},
number = {1},
doi = {10.1186/s13677-026-00939-w},
url = {https://doi.org/10.1186/s13677-026-00939-w}
}
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
- small language models
- inference privacy
- inference attacks
- privacy-utility trade-off
- privacy-preserving inference
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?
Wang, F., Li, D., Ma, B., Wang, X., Li, C., Qi, X., Zhang, Y., Sha, K., Chen, H., & Yu, G. (2026). Selective semantic state editing for private edge-cloud inference in SLMs. Journal of Cloud Computing Advances Systems and Applications, 15(1). https://doi.org/10.1186/s13677-026-00939-w
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 Journal of Cloud Computing Advances Systems and Applications: sign in and open the full text from this page.
Who wrote this paper?
Feifan Wang, Delong Li, Baihe Ma, Xu Wang, Chen Li, Xuelei Qi, Yang Zhang, Kewei Sha, Haihua Chen, Guangsheng Yu.
What is the DOI of this paper?
10.1186/s13677-026-00939-w, permanently at https://doi.org/10.1186/s13677-026-00939-w. 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.