Browsing by Author "Torfi, Amirsina"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Differentially private synthetic medical data generation using convolutional gans
    Torfi, Amirsina; Fox, Edward A.; Reddy, Chandan K. (Elsevier, 2022)
    Deep learning models have demonstrated superior performance in several real-world application problems such as image classification and speech processing. However, creating these models in sensitive domains like healthcare typically requires addressing certain privacy challenges that bring unique concerns. One effective way to handle such private data concerns is to generate realistic synthetic data that can provide practically acceptable data quality as well as be used to improve model performance. To tackle this challenge, we develop a differentially private framework for synthetic data generation using Rényi differential privacy. Our approach builds on convolutional autoencoders and convolutional generative adversarial networks to preserve critical characteristics of the generated synthetic data. In addition, our model can capture the temporal information and feature correlations present in the original data. We demonstrate that our model outperforms existing state-of-the-art models under the same privacy budget using several publicly available benchmark medical datasets in both supervised and unsupervised settings. The source code of this work is available at https://github.com/astorfi/differentially-private-cgan.
  • Thumbnail Image
    Generating Synthetic Healthcare Records Using Convolutional Generative Adversarial Networks
    Torfi, Amirsina; Beyki, Mohammadreza (Virginia Tech, 2019-12-20)
    Deep learning models have demonstrated high-quality performance in several areas such as image classification and speech processing. However, creating a deep learning model using electronic health record (EHR) data requires addressing particular privacy challenges that make this issue unique to researchers in this domain. This matter focuses attention on generating realistic synthetic data to amplify privacy. Existing methods for artificial data generation suffer from different limitations such as being bound to particular use cases. Furthermore, their generalizability to real-world problems is controversial regarding the uncertainties in defining and measuring key realistic characteristics. Henceforth, there is a need to establish insightful metrics (and to measure the validity of synthetic data), as well as quantitative criteria regarding privacy restrictions. We propose the use of Generative Adversarial Networks to help satisfy requirements for realistic characteristics and acceptable values of privacy metrics simultaneously. The present study makes several unique contributions to synthetic data generation in the healthcare domain. First, utilizing 1-D Convolutional Neural Networks (CNNs), we devise a new approach to capturing the correlation between adjacent diagnosis records. Second, we employ convolutional autoencoders to map the discrete-continuous values. Finally, we devise a new approach to measure the similarity between real and synthetic data, and a means to measure the fidelity of the synthetic data and its associated privacy risks.
  • Thumbnail Image
    Nearest Neighbor Classifier – From Theory to Practice
    Torfi, Amirsina (Machine Learning Mindset, 2020-01-11)
    The K-nearest neighbors (KNNs) classifier or simply Nearest Neighbor Classifier is a kind of supervised machine learning algorithm that operates based on spatial distance measurements. In this article, we investigate the theory behind it. Furthermore, a working example of the k-nearest neighbor classifier will be represented.
  • Thumbnail Image
    Privacy-Preserving Synthetic Medical Data Generation with Deep Learning
    Torfi, Amirsina (Virginia Tech, 2020-08-26)
    Deep learning models demonstrated good performance in various domains such as ComputerVision and Natural Language Processing. However, the utilization of data-driven methods in healthcare raises privacy concerns, which creates limitations for collaborative research. A remedy to this problem is to generate and employ synthetic data to address privacy concerns. Existing methods for artificial data generation suffer from different limitations, such as being bound to particular use cases. Furthermore, their generalizability to real-world problems is controversial regarding the uncertainties in defining and measuring key realistic characteristics. Hence, there is a need to establish insightful metrics (and to measure the validity of synthetic data), as well as quantitative criteria regarding privacy restrictions. We propose the use of Generative Adversarial Networks to help satisfy requirements for realistic characteristics and acceptable values of privacy metrics, simultaneously. The present study makes several unique contributions to synthetic data generation in the healthcare domain. First, we propose a novel domain-agnostic metric to evaluate the quality of synthetic data. Second, by utilizing 1-D Convolutional Neural Networks, we devise a new approach to capturing the correlation between adjacent diagnosis records. Third, we employ ConvolutionalAutoencoders for creating a robust and compact feature space to handle the mixture of discrete and continuous data. Finally, we devise a privacy-preserving framework that enforcesRényi differential privacy as a new notion of differential privacy.