An Efficient DP-SGD Mechanism for Large Scale NLP Models

by   Christophe Dupuy, et al.

Recent advances in deep learning have drastically improved performance on many Natural Language Understanding (NLU) tasks. However, the data used to train NLU models may contain private information such as addresses or phone numbers, particularly when drawn from human subjects. It is desirable that underlying models do not expose private information contained in the training data. Differentially Private Stochastic Gradient Descent (DP-SGD) has been proposed as a mechanism to build privacy-preserving models. However, DP-SGD can be prohibitively slow to train. In this work, we propose a more efficient DP-SGD for training using a GPU infrastructure and apply it to fine-tuning models based on LSTM and transformer architectures. We report faster training times, alongside accuracy, theoretical privacy guarantees and success of Membership inference attacks for our models and observe that fine-tuning with proposed variant of DP-SGD can yield competitive models without significant degradation in training time and improvement in privacy protection. We also make observations such as looser theoretical ϵ, δ can translate into significant practical privacy gains.


Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search

Models need to be trained with privacy-preserving learning algorithms to...

Per-Instance Privacy Accounting for Differentially Private Stochastic Gradient Descent

Differentially private stochastic gradient descent (DP-SGD) is the workh...

DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass

Differentially private stochastic gradient descent (DP-SGD) adds noise t...

Large Language Models Can Be Strong Differentially Private Learners

Differentially Private (DP) learning has seen limited success for buildi...

One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks

Preserving privacy in training modern NLP models comes at a cost. We kno...

EW-Tune: A Framework for Privately Fine-Tuning Large Language Models with Differential Privacy

Pre-trained Large Language Models (LLMs) are an integral part of modern ...

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping

Machine learning algorithms are vulnerable to data poisoning attacks. Pr...

Please sign up or login with your details

Forgot password? Click here to reset