A Privacy Study of Sparse Collaborative Inference

2026-08-17 · Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek arxiv

Collaborative inference (CI) splits a model between an edge device and a server, whereby the client computes an intermediate activation, transmits it, and the server completes the computation. This raises two concerns, the communication cost of the transmission and the risk that it reveals private information about the input. Recent work reduces this cost by sparsifying activations and entropy-coding the result. Sparsity has also been argued to improve privacy, on the intuition that transmitting fewer values reveals less about the input. We test this claim by decomposing the sparse activation into the retained values and the set of positions they occupy, and by reconstructing inputs from each component in isolation. We find that sparsification reduces the leakage far less than it reduces the transmission cost, and that the remaining risk shifts to the positions, which prior analyses treat as side information for decoding. Across natural-image and face datasets, the positions alone constitute a serious privacy risk, enabling high-fidelity reconstructions and re-identification of individuals. The leakage from the positions persists even when both the transmission cost and the task utility are low. We conclude that the positions of sparse activations should be treated as sensitive transmitted data and audited carefully in the context of collaborative inference. Code is available at https://github.com/an7123/Privacy-Study-Sparse-CI.

📄 PDF Abstract BibTeX arXiv:2608.16236

Code (0)

등록된 구현이 없습니다.

PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks

2023-07-20 · Shiwei Ding, Lan Zhang, Miao Pan, Xiaoyong Yuan

Collaborative inference has been a promising solution to enable resource-constrained edge devices to perform inference using state-of-the-art deep neural networks (DNNs). In collaborative inference, the edge device first…

Collaborative Inference Vehicle Re-Identification

Privacy-Preserving Optimal Parameter Selection for Collaborative Clustering

2024-06-08 · Maryam Ghasemian, Erman Ayday

This study investigates the optimal selection of parameters for collaborative clustering while ensuring data privacy. We focus on key clustering algorithms within a collaborative framework, where multiple data owners com…

Clustering Privacy Preserving

PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information

2023-05-17 · Lin Duan, Jingwei Sun, Yiran Chen, Maria Gorlatova

Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research …

Collaborative Inference

Private Collaborative Edge Inference via Over-the-Air Computation

2024-07-30 · Selim F. Yilmaz, Burak Hasircioglu, Li Qiao, Deniz Gunduz

We consider collaborative inference at the wireless edge, where each client's model is trained independently on its local dataset. Clients are queried in parallel to make an accurate decision collaboratively. In addition…

Collaborative Inference

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

2023-04-06 · Yuke Hu, Wei Liang, Ruofan Wu, Kai Xiao 외

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging federated KGE (FKGE) collaboratively train…

Graph Embedding Knowledge Graph Embedding