Chapter 13 Privacy Preserving Abnormality Detection: A Deep Learning Approach Wenyu Han, Amin Azmoodeh, Hadis Karimipour, and Simon Yang 1 Introduction Artificial Intelligence (AI) is the concept used to describe computer systems that can learn from their own experiences and solve complex problems in different situations [1]. Around 2010, the field of AI has been shaken by the broad and unforeseen successes of multi-layer Neural Networks (NNs). This success is due to the introduction of high performance computing, Graphic Processing Unit (GPUs), and the availability of large labeled data sets that could be used as training testbeds. This combination has allowed the rise of Deep Learning (DL) on Deep Neural Networks (DNNs), especially on the architecture called Convolutional Neural Networks (CNNs) [2, 3]. The development of AI has made major advances in recent years and its potential appears to be promising. In the healthcare sector, scientific competitions like ImageNet large-scale visual recognition challenges are providing evidence that computers can achieve human-like competence in image recognition. Researches demonstrated that AI is able to make clinical diagnoses at levels equal to clinicians in some specific cases using medical images [4, 5]. This venture will have a considerable impact on healthcare operation, manage- ment and research. However, there are still barriers and challenges that need to be addressed. Several growing trends in the healthcare, such as clinician mobility and wireless networking, health information exchange, and cloud computing are W. Han · H. Karimipour () · S. Yang School of Engineering, University of Guelph, Guelph, ON, Canada e-mail: whan01@uoguelph.ca; hkarimi@uoguelph.ca; Canada-hkarimi@uoguelph.ca; syang@uoguelph.ca A. Azmoodeh Cyber Science Lab, School of Computer Science, University of Guelph, Guelph, ON, Canada e-mail: amin@cybersciencelab.org © Springer Nature Switzerland AG 2020 K.-K. R. Choo, A. Dehghantanha (eds.), Handbook of Big Data Privacy, https://doi.org/10.1007/978-3-030-38557-6_13 285