A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edge

• URL: http://arxiv.org/abs/2512.09309v1
• Date: Wed, 10 Dec 2025 04:37:07 GMT
• Title: A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edge
• Authors: Zihao Ding, Mufeng Zhu, Zhongze Tang, Sheng Wei, Yao Liu,
• Abstract summary: We propose a distributed, hierarchical offloading framework for Vision Transformers (ViTs)<n>Our approach uses a local trusted edge device, such as a mobile phone or an Nvidia Jetson, as the edge orchestrator.<n>By design, no single external server possesses the complete image, preventing comprehensive data reconstruction.
• Score: 3.344634520578015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Nowadays, visual intelligence tools have become ubiquitous, offering all kinds of convenience and possibilities. However, these tools have high computational requirements that exceed the capabilities of resource-constrained mobile and wearable devices. While offloading visual data to the cloud is a common solution, it introduces significant privacy vulnerabilities during transmission and server-side computation. To address this, we propose a novel distributed, hierarchical offloading framework for Vision Transformers (ViTs) that addresses these privacy challenges by design. Our approach uses a local trusted edge device, such as a mobile phone or an Nvidia Jetson, as the edge orchestrator. This orchestrator partitions the user's visual data into smaller portions and distributes them across multiple independent cloud servers. By design, no single external server possesses the complete image, preventing comprehensive data reconstruction. The final data merging and aggregation computation occurs exclusively on the user's trusted edge device. We apply our framework to the Segment Anything Model (SAM) as a practical case study, which demonstrates that our method substantially enhances content privacy over traditional cloud-based approaches. Evaluations show our framework maintains near-baseline segmentation performance while substantially reducing the risk of content reconstruction and user data exposure. Our framework provides a scalable, privacy-preserving solution for vision tasks in the edge-cloud continuum.

Related papers

• Mobile-VTON: High-Fidelity On-Device Virtual Try-On [75.5009105664896]
  Mobile-VTON is a high-quality, privacy-preserving framework for virtual try-on.<n>It enables fully offline virtual try-on on commodity mobile devices using only a single user image and a garment image.
  arXiv  Detail & Related papers  (2026-03-01T06:36:13Z)
• ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation [9.081441952478306]
  ObCLIP is a plug-and-play safeguard for oblivious cloud-device hybrid generation.<n>It provides rigorous privacy and comparable utility to cloud models with slightly increased server cost.
  arXiv  Detail & Related papers  (2025-10-05T11:09:10Z)
• Personalized Vision via Visual In-Context Learning [62.85784251383279]
  We present a visual in-context learning framework for personalized vision.<n>PICO infers the underlying transformation and applies it to new inputs without retraining.<n>We also propose an attention-guided seed scorer that improves reliability via efficient inference scaling.
  arXiv  Detail & Related papers  (2025-09-29T17:58:45Z)
• CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering [80.54309860395763]
  CoSteer is a novel collaborative framework that enables decoding-time personalization through localized delta steering.<n>We formulate token-level optimization as an online learning problem, where local delta vectors dynamically adjust the remote LLM's logits.<n>This approach preserves privacy by transmitting only the final steered tokens rather than raw data or intermediate vectors.
  arXiv  Detail & Related papers  (2025-07-07T08:32:29Z)
• PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts [59.5243730853157]
  Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns.<n>Small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks.<n>We propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework to balance computational cost, performance, and privacy protection under bandwidth constraints.
  arXiv  Detail & Related papers  (2025-05-13T16:27:07Z)
• Privacy preserving layer partitioning for Deep Neural Network models [0.21470800327528838]
  Trusted Execution Environments (TEEs) can introduce significant performance overhead due to additional layers of encryption, decryption, security and integrity checks. We introduce layer partitioning technique and offloading computations to GPU. We conduct experiments to demonstrate the effectiveness of our approach in protecting against input reconstruction attacks developed using trained conditional Generative Adversarial Network(c-GAN)
  arXiv  Detail & Related papers  (2024-04-11T02:39:48Z)
• MAGNETO: Edge AI for Human Activity Recognition -- Privacy and Personalization [1.494944639485053]
  MAGNETO is an Edge AI platform that pushes HAR tasks from the Cloud to the Edge. This enables strong privacy guarantees, low processing latency, and a high degree of personalization for users.
  arXiv  Detail & Related papers  (2024-02-11T12:29:16Z)
• FLVoogd: Robust And Privacy Preserving Federated Learning [12.568409209047505]
  We proposeoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy. Servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with S2PC to cluster the benign majority without acquiring sensitive personal information. Our framework is automatic and adaptive that servers/clients don't need to tune the parameters during the training.
  arXiv  Detail & Related papers  (2022-06-24T08:48:15Z)
• Auto-Split: A General Framework of Collaborative Edge-Cloud AI [49.750972428032355]
  This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.
  arXiv  Detail & Related papers  (2021-08-30T08:03:29Z)
• Efficient Privacy Preserving Edge Computing Framework for Image Classification [2.6514980627603006]
  A novel privacy preserving edge computing framework is proposed in this paper for image classification. Autoencoder will be trained unsupervised at each edge device individually, then the obtained latent vectors will be transmitted to the edge server. The privacy of the end users' data is protected by transmitting latent vectors without additional cost of encryption.
  arXiv  Detail & Related papers  (2020-05-10T03:36:32Z)
• A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service [68.84245063902908]
  This paper introduces a novel distributed architecture for deep-learning-as-a-service. It is able to preserve the user sensitive data while providing Cloud-based machine and deep learning services.
  arXiv  Detail & Related papers  (2020-03-30T15:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.