يتم تطبيق مصنف النصوص بانتظام على النصوص الشخصية، وترك مستخدمي هذه المصنفين عرضة لخرق الخصوصية.نقترح حلا لتصنيف النص الذي يحفظه الخصوصية التي تعتمد على الشبكات العصبية التنافعية (CNNS) والحساب الآمن متعدد الأحزاب (MPC).تتيح طريقتنا استنتاج تسمية فئة لنص شخصي بهذه الطريقة (1) لا يتعين على مالك النص الشخصي الكشف عن نصها لأي شخص بطريقة غير مشفرة، و (2) مالك النصلا يتعين على المصنف أن يكشف عن المعلمات النموذجية المدربة إلى مالك النص أو أي شخص آخر.لإظهار جدوى بروتوكولنا لتصنيف النص الخاص العملي، نفذناها في Fronten Fresk Framepten المستندة إلى Pytorch، باستخدام مخطط تقاسم سري معروف جيدا في الإعداد الصادق وغير الغريب.نحن نختبر وقت تشغيل مصنف نصي المحفوظ في الخصوصية لدينا، وهو سريع بما يكفي لاستخدامه في الممارسة العملية.
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 Neural Networks (CNNs) and Secure Multiparty Computation (MPC). Our method enables the inference of a class label for a personal text in such a way that (1) the owner of the personal text does not have to disclose their text to anyone in an unencrypted manner, and (2) the owner of the text classifier does not have to reveal the trained model parameters to the text owner or to anyone else. To demonstrate the feasibility of our protocol for practical private text classification, we implemented it in the PyTorch-based MPC framework CrypTen, using a well-known additive secret sharing scheme in the honest-but-curious setting. We test the runtime of our privacy-preserving text classifier, which is fast enough to be used in practice.
References used
https://aclanthology.org/
We study the problem of domain adaptation in Neural Machine Translation (NMT) when domain-specific data cannot be shared due to confidentiality or copyright issues. As a first step, we propose to fragment data into phrase pairs and use a random sampl
In recent years, the problem of classifying objects in images has increased by using deep learning as a result of the industrial sector requirements. Despite of many algorithms used in this field, such as Deep Learning Neural Network DNN and Convolut
The deep learning algorithm has recently achieved a lot of success, especially in the field of computer vision. This research aims to describe the classification method applied to the dataset of multiple types of images (Synthetic Aperture Radar (SAR
Hope is an essential aspect of mental health stability and recovery in every individual in this fast-changing world. Any tools and methods developed for detection, analysis, and generation of hope speech will be beneficial. In this paper, we propose
Fine-grained temporal relation extraction (FineTempRel) aims to recognize the durations and timeline of event mentions in text. A missing part in the current deep learning models for FineTempRel is their failure to exploit the syntactic structures of