Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble

2024-01-19 · Dancheng Liu, Chenhui Xu, Jiajie Li, Amir Nassereldine, JinJun Xiong

For collaborative inference through a cloud computing platform, it is sometimes essential for the client to shield its sensitive information from the cloud provider. In this paper, we introduce Ensembler, an extensible framework designed to substantially increase the difficulty of conducting model inversion attacks by adversarial parties. Ensembler leverages selective model ensemble on the adversarial server to obfuscate the reconstruction of the client's private information. Our experiments demonstrate that Ensembler can effectively shield input images from reconstruction attacks, even when the client only retains one layer of the network locally. Ensembler significantly outperforms baseline methods by up to 43.5% in structural similarity while only incurring 4.8% time overhead during inference.

📄 PDF Abstract BibTeX arXiv:2401.10859

Code (0)

등록된 구현이 없습니다.

Tasks

Cloud ComputingCollaborative Inference

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

Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learning

2025-08-16 · Xiaojin Zhang, Mingcong Xu, Yiming Li, Wei Chen 외 arxiv

Federated learning (FL) offers a promising paradigm for collaborative model training while preserving data privacy. However, its susceptibility to gradient inversion attacks poses a significant challenge, necessitating r…

Federated Learning

Collaborative Drug Discovery: Inference-level Data Protection Perspective

2022-05-13 · Balazs Pejo, Mina Remeli, Adam Arany, Mathieu Galtier 외

Pharmaceutical industry can better leverage its data assets to virtualize drug discovery through a collaborative machine learning platform. On the other hand, there are non-negligible risks stemming from the unintended l…

Drug Discovery Privacy Preserving

QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning

2024-11-08 · Md Jueal Mia, M. Hadi Amini

Federated Learning has emerged as a leading approach for decentralized machine learning, enabling multiple clients to collaboratively train a shared model without exchanging private data. While FL enhances data privacy, …

Computational Efficiency Federated Learning Quantization

SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition

2025-10-01 · Chenxiang Luo, David K. Y. Yau, Qun Song arxiv

Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where adversaries reconstruct private data from shared gradients. Existing def…

Human Activity Recognition Image Classification Federated Learning Keyword Spotting