Privacy-Preserving Graph Convolutional Networks for Text Classification
Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or social networks. However, sensitive personal information, such as documents with people's profiles or relationships as edges, are prone to privacy leaks, as the trained model might reveal the original input. Although differential privacy (DP) offers a well-founded privacy-preserving framework, GCNs pose theoretical and practical challenges due to their training specifics. We address these challenges by adapting differentially-private gradient-based training to GCNs and conduct experiments using two optimizers on five NLP datasets in two languages. We propose a simple yet efficient method based on random graph splits that not only improves the baseline privacy bounds by a factor of 2.7 while retaining competitive F1 scores, but also provides strong privacy guarantees of epsilon = 1.0. We show that, under certain modeling choices, privacy-preserving GCNs perform up to 90% of their non-private variants, while formally guaranteeing strong privacy measures.
Code (1)
Tasks
ClassificationGeneral ClassificationPrivacy PreservingRepresentation Learningtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Privacy-Preserving Graph Convolutional Networks for Text Classification
Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or social networks. However, sensitive personal information, such as…
ClassificationPrivacy PreservingRepresentation Learningtext-classification+1Private Text Classification with Convolutional Neural Networks
Text classifiers are regularly applied to personal texts, leaving users of these classifiers vulnerable to privacy breaches. We propose a solution for privacy-preserving text classification that is based on Convolutional…
ClassificationPrivacy Preservingtext-classificationText ClassificationPrivacy-Preserving Video Classification with Convolutional Neural Networks
Many video classification applications require access to personal data, thereby posing an invasive security risk to the users' privacy. We propose a privacy-preserving implementation of single-frame method based video cl…
ClassificationEmotion RecognitionGeneral Classificationimage-classification+3Misclassification Rate and Privacy-Utility Trade-offs in Graph Convolutional Networks via Subsampling Stability
We study differential privacy (DP) in Graph Convolutional Networks (GCNs) through the framework of \textit{subsampling stability}. We derive upper bounds on the misclassification rate that depend explicitly on the subsam…
Reducing ReLU Count for Privacy-Preserving CNN Speedup
Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Network…
BIG-bench Machine LearningPrivacy Preserving