GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference
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.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Feature Space Hijacking Attacks against Differentially Private Split Learning
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 ReductionSecure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attacks
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 PreservingUnleashing the Tiger: Inference Attacks on Split Learning
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 LearningA Hybrid Quantum Neural Network for Split Learning
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 LearningPassive Inference Attacks on Split Learning via Adversarial Regularization
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