paper-with-me

홈 › Papers

GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference

2023-09-21 · NeurIPS 2023 11

Split Inference (SI) is an emerging deep learning paradigm that addresses computational constraints on edge devices and preserves data privacy through collaborative edge-cloud approaches. However, SI is vulnerable to Data Reconstruction Attacks (DRA), which aim to reconstruct users' private prediction instances. Existing attack methods suffer from various limitations. Optimization-based DRAs do not leverage public data effectively, while Learning-based DRAs depend heavily on auxiliary data quantity and distribution similarity. Consequently, these approaches yield unsatisfactory attack results and are sensitive to defense mechanisms. To overcome these challenges, we propose a GAN-based LAtent Space Search attack (GLASS) that harnesses abundant prior knowledge from public data using advanced StyleGAN technologies. Additionally, we introduce GLASS++ to enhance reconstruction stability. Our approach represents the first GAN-based DRA against SI, and extensive evaluation across different split points and adversary setups demonstrates its state-of-the-art performance. Moreover, we thoroughly examine seven defense mechanisms, highlighting our method's capability to reveal private information even in the presence of these defenses.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Adaptive Instance Normalization 설명 없음
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
StyleGAN 설명 없음

Similar Papers 제목 키워드 기반

Feature Space Hijacking Attacks against Differentially Private Split Learning

2022-01-11 · Grzegorz Gawron, Philip Stubbings

Split learning and differential privacy are technologies with growing potential to help with privacy-compliant advanced analytics on distributed datasets. Attacks against split learning are an important evaluation tool a…

Dimensionality Reduction

Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attacks

2023-04-19 · Yunlong Mao, Zexi Xin, Zhenyu Li, Jue Hong 외

Split learning of deep neural networks (SplitNN) has provided a promising solution to learning jointly for the mutual interest of a guest and a host, which may come from different backgrounds, holding features partitione…

Privacy Preserving

Unleashing the Tiger: Inference Attacks on Split Learning

2020-12-04 · Dario Pasquini, Giuseppe Ateniese, Massimo Bernaschi

We investigate the security of Split Learning -- a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities …

Federated Learning

A Hybrid Quantum Neural Network for Split Learning

2024-09-25 · Hevish Cowlessur, Chandra Thapa, Tansu Alpcan, Seyit Camtepe

Quantum Machine Learning (QML) is an emerging field of research with potential applications to distributed collaborative learning, such as Split Learning (SL). SL allows resource-constrained clients to collaboratively tr…

Quantum Machine Learning

Passive Inference Attacks on Split Learning via Adversarial Regularization

2023-10-16 · Xiaochen Zhu, Xinjian Luo, Yuncheng Wu, Yangfan Jiang 외

Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong assumptions or targeted easily exploitab…

Federated Learning