With the increasing use of cloud-based services for training and deploying
machine learning models, data privacy has become a major concern. This is
particularly important for natural language processing (NLP) models, which
often process sensitive information such as personal communications and
confidential documents. In this study, we propose a method for training NLP
models on encrypted text data to mitigate data privacy concerns while
maintaining similar performance to models trained on non-encrypted data. We
demonstrate our method using two different architectures, namely
Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups
dataset. Our results indicate that both encrypted and non-encrypted models
achieve comparable performance, suggesting that our encryption method is
effective in preserving data privacy without sacrificing model accuracy. In
order to replicate our experiments, we have provided a Colab notebook at the
following address: this https URL

该研究提出了一种使用加密文本数据训练自然语言处理模型的方法，以解决隐私问题，并展示了加密和非加密模型在性能上的可比性。

在加密文本上训练自然语言处理模型以提高隐私性

Training Natural Language Processing Models on Encrypted Text for  Enhanced Privacy

The trend towards the cloudification of the 3GPP LTE mobile network
architecture and the emergence of federated cloud infrastructures call for
alternative service delivery strategies for improved user experience and
efficient resource utilization. We propose Follow-Me Cloud (FMC), a design
tailored to this environment, but with a broader applicability, which allows
mobile users to always be connected via the optimal data anchor and mobility
gateways, while cloud-based services follow them and are delivered via the
optimal service point inside the cloud infrastructure. FMC applies a
Markov-Decision-Process-based algorithm for cost-effective,
performance-optimized service migration decisions, while two alternative
schemes to ensure service continuity and disruption-free operation are
proposed, based on either Software Defined Networking technologies or the
Locator/Identifier Separation Protocol. Numerical results from our analytic
model for FMC, as well as testbed experiments with the two alternative FMC
implementations we have developed, demonstrate quantitatively and qualitatively
the advantages it can bring about.

Follow-Me Cloud (FMC) is a design for cloudification of the 3GPP LTE mobile network architecture, providing users with optimal data anchor and mobility gateways, and cost-effective, performance-optimized service migration decisions through Markov-Decision-Process-based algorithm, with two alternative schemes for service continuity based on Software Defined Networking or Locator/Identifier Separation Protocol.

跟随我云：当云服务跟随移动用户

Follow-Me Cloud: When Cloud Services Follow Mobile Users

As machine learning becomes a practice and commodity, numerous cloud-based
services and frameworks are provided to help customers develop and deploy
machine learning applications. While it is prevalent to outsource model
training and serving tasks in the cloud, it is important to protect the privacy
of sensitive samples in the training dataset and prevent information leakage to
untrusted third parties. Past work have shown that a malicious machine learning
service provider or end user can easily extract critical information about the
training samples, from the model parameters or even just model outputs.
In this paper, we propose a novel and generic methodology to preserve the
privacy of training data in machine learning applications. Specifically we
introduce an obfuscate function and apply it to the training data before
feeding them to the model training task. This function adds random noise to
existing samples, or augments the dataset with new samples. By doing so
sensitive information about the properties of individual samples, or
statistical properties of a group of samples, is hidden. Meanwhile the model
trained from the obfuscated dataset can still achieve high accuracy. With this
approach, the customers can safely disclose the data or models to third-party
providers or end users without the need to worry about data privacy. Our
experiments show that this approach can effective defeat four existing types of
machine learning privacy attacks at negligible accuracy cost.

该论文提出了一种新的通用方法 —— 混淆函数，可在不泄露机器学习训练数据的前提下保护其中的隐私信息，并成功地抵御了四种现有的机器学习隐私攻击。