Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient Matching
Recent works have demonstrated that it is possible to reconstruct training images and their labels from gradients of an image-classification model when its architecture is known. Unfortunately, there is still an incomplete theoretical understanding of the efficacy and failure of these gradient-leakage attacks. In this paper, we propose a novel framework to analyse training-data leakage from gradients that draws insights from both analytic and optimisation-based gradient-leakage attacks. We formulate the reconstruction problem as solving a linear system from each layer iteratively, accompanied by corrections using gradient matching. Under this framework, we claim that the solubility of the reconstruction problem is primarily determined by that of the linear system at each layer. As a result, we are able to partially attribute the leakage of the training data in a deep network to its architecture. We also propose a metric to measure the level of security of a deep learning model against gradient-based attacks on the training data.
Code (1)
Tasks
Attributeimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previ…
CAFE: Catastrophic Data Leakage in Federated Learning
Private training data can be leaked through the gradient sharing mechanism deployed in machine learning systems, such as federated learning (FL). Increasing batch size is often viewed as a promising defense strategy agai…
Federated LearningCatastrophic Data Leakage in Vertical Federated Learning
Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate …
Federated LearningVertical Federated LearningCAFE: Catastrophic Data Leakage in Vertical Federated Learning
Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate …
Federated LearningVertical Federated LearningAnalysing the Influence of Attack Configurations on the Reconstruction of Medical Images in Federated Learning
The idea of federated learning is to train deep neural network models collaboratively and share them with multiple participants without exposing their private training data to each other. This is highly attractive in the…
Federated Learning