Differential Privacy for Transformer Embeddings of Text with Nonparametric Variational Information Bottleneck
We propose a privacy-preserving method for sharing text data by sharing noisy versions of their transformer embeddings. It has been shown that hidden representations learned by deep models can encode sensitive information from the input, making it possible for adversaries to recover the input data with considerable accuracy. This problem is exacerbated in transformer embeddings because they consist of multiple vectors, one per token. To mitigate this risk, we propose Nonparametric Variational Differential Privacy (NVDP), which ensures both useful data sharing and strong privacy protection. We take a differential privacy (DP) approach, integrating a nonparametric variational information bottleneck (NVIB) layer into the transformer architecture to inject noise into its multivector embeddings and thereby hide information, and measuring privacy protection with Rényi Divergence (RD) and its corresponding Bayesian Differential Privacy (BDP) guarantee. Training the NVIB layer calibrates the noise level according to the utility of the downstream task. We test NVDP on the General Language Understanding Evaluation (GLUE) benchmark and show that varying the noise level gives us a useful trade-off between privacy and accuracy. With lower noise levels, our model maintains high accuracy while offering strong privacy guarantees, effectively balancing privacy and utility.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints
This paper studies federated learning for nonparametric regression in the context of distributed samples across different servers, each adhering to distinct differential privacy constraints. The setting we consider is he…
Federated LearningPrivacy PreservingregressionDifferential Privacy in Personalized Pricing with Nonparametric Demand Models
In the recent decades, the advance of information technology and abundant personal data facilitate the application of algorithmic personalized pricing. However, this leads to the growing concern of potential violation of…
Adversarial AttackA Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck
We propose a VAE for Transformers by developing a variational information bottleneck regulariser for Transformer embeddings. We formalise the embedding space of Transformer encoders as mixture probability distributions, …
DecoderMinimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraints
This paper considers minimax and adaptive transfer learning for nonparametric classification under the posterior drift model with distributed differential privacy constraints. Our study is conducted within a heterogeneou…
ClassificationTransfer LearningNonparametric Variational Differential Privacy via Embedding Parameter Clipping
The nonparametric variational information bottleneck (NVIB) provides the foundation for nonparametric variational differential privacy (NVDP), a framework for building privacy-preserving language models. However, the lea…