DP-ANN: A new Differential Private Artificial Neural Network with Application on Health data (Workshop Paper)

Privacy of the individual data, especially in the Health data, is very sensitive and important. Privacy preserving Machine learning is emerging as one of the solutions for the security of data with the utility to create knowledge. In this paper, we have proposed a differential private artificial neural network (DP-ANN) and shows its application to predict the spread and the peak number of COVID-19 cases. We proposed a differential private artificial neural network (DP-ANN) in which laplacian noise has been introduced at activation function level and it has been compared with existing privacy ideas at error function and weights level of ANN. Results show that DP-ANN model with the private activation function produces the result similar to the base ANN model.

[1]  Mahmood Akhtar,et al.  A dynamic neural network model for predicting risk of Zika in real time , 2019, BMC Medicine.

[2]  Sangwon Chae,et al.  Predicting Infectious Disease Using Deep Learning and Big Data , 2018, International journal of environmental research and public health.

[3]  A. Gandomi,et al.  Time Series Analysis and Forecast of the COVID-19 Pandemic in India using Genetic Programming , 2020, Chaos, Solitons & Fractals.

[4]  Parikshit N. Mahalle,et al.  Predictive Analytics of COVID-19 Using Information, Communication and Technologies , 2020 .

[5]  G. Pandey,et al.  SEIR and Regression Model based COVID-19 outbreak predictions in India , 2020, medRxiv.

[6]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.

[7]  Sonali Agarwal,et al.  COVID-19 Epidemic Analysis using Machine Learning and Deep Learning Algorithms , 2020, medRxiv.

[8]  Charles Elkan,et al.  Differential Privacy and Machine Learning: a Survey and Review , 2014, ArXiv.

[9]  Vitaly Shmatikov,et al.  Membership Inference Attacks Against Machine Learning Models , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[10]  Vitaly Shmatikov,et al.  Privacy-preserving deep learning , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[11]  Aboul Ella Hassanien,et al.  A machine learning forecasting model for COVID-19 pandemic in India , 2020, Stochastic Environmental Research and Risk Assessment.

[12]  S. Tuli,et al.  Predicting the growth and trend of COVID-19 pandemic using machine learning and cloud computing , 2020, Internet of Things.

[13]  Anand D. Sarwate,et al.  Stochastic gradient descent with differentially private updates , 2013, 2013 IEEE Global Conference on Signal and Information Processing.

[14]  Sushil Kumar,et al.  Outbreak Trends of Coronavirus Disease–2019 in India: A Prediction , 2020, Disaster Medicine and Public Health Preparedness.

[15]  R. Gupta,et al.  ARIMA and NAR based prediction model for time series analysis of COVID-19 cases in India , 2020, Journal of Safety Science and Resilience.

[16]  Calton Pu,et al.  Differentially Private Model Publishing for Deep Learning , 2019, 2019 IEEE Symposium on Security and Privacy (SP).

[17]  Dejing Dou,et al.  Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[18]  S. Sengupta,et al.  Covid-19 Pandemic Data Analysis and Forecasting using Machine Learning Algorithms , 2020, medRxiv.

[19]  A. MOSAVI,et al.  COVID-19 Outbreak Prediction with Machine Learning , 2020, medRxiv.

[20]  Neeraj Gupta,et al.  Prediction for the spread of COVID-19 in India and effectiveness of preventive measures , 2020, Science of The Total Environment.

[21]  Parikshit N. Mahalle,et al.  Epidemic Peak for COVID-19 in India, 2020 , 2020 .

[22]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.