How reparametrization trick broke differentially-private text representation learning
As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods. One of the favorite privacy frameworks, differential privacy (DP), is perhaps the most compelling thanks to its fundamental theoretical guarantees. Despite the apparent simplicity of the general concept of differential privacy, it seems non-trivial to get it right when applying it to NLP. In this short paper, we formally analyze several recent NLP papers proposing text representation learning using DPText (Beigi et al., 2019a,b; Alnasser et al., 2021; Beigi et al., 2021) and reveal their false claims of being differentially private. Furthermore, we also show a simple yet general empirical sanity check to determine whether a given implementation of a DP mechanism almost certainly violates the privacy loss guarantees. Our main goal is to raise awareness and help the community understand potential pitfalls of applying differential privacy to text representation learning.
Code (1)
Tasks
Privacy PreservingRepresentation LearningSimilar Papers 제목 키워드 기반
Large Scale Private Learning via Low-rank Reparametrization
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffe…
A Scalable Laplace Approximation for Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace and more
Bayesian InferencePreconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace and more
spred: Solving $L_1$ Penalty with SGD
We propose to minimize a generic differentiable objective with $L_1$ constraint using a simple reparametrization and straightforward stochastic gradient descent. Our proposal is the direct generalization of previous idea…
Inductive BiasNeural Network CompressionAn Empirical Analysis of Measure-Valued Derivatives for Policy Gradients
Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial…