درخت حوزه‌های تخصصی

In recent privacy has emerged as one of the major concerns of deep learning, since it requires huge amount of personal data. Medical Image Analysis is one of the prominent areas where sensitive data are shared to a third party service provider. In this paper, a secure deep learning scheme called Metamorphosed Learning (MpLe) is proposed to protect the privacy of images in medical image analysis. An augmented convolutional layer and image morphing are two main components of MpLe scheme. Data providers morph the images without privacy information using image morphing component. The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty. MpLe provides sturdy security and privacy with optimal computational overhead. The proposed scheme is experimented using VGG-16 network on CIFAR dataset. The performance of MpLe is compared with similar works such as GAZELLE and MiniONN and found that the MpLe attracts very less computational and data transmission overhead. MpLe is also analyzed for various adversarial attack and realized that the success rate is as low as . The efficiency of the proposed scheme is proved through experimental and performance analysis.

The purpose of this research is to provide a model for reporting quality of financial information based on behavioral and value accounting of listed companies in Tehran Stock Exchange which is based on Structural Equation Modeling. This research in terms of applied purpose is applied research and in terms of data collection method is post-semi experimental research in the field of proofing accounting research with deductive- inductive approach. The statistical population of this is including the sample of 128 listed companies in the Tehran Stock Exchange between 2007 and 2017. The behavioral characteristics of managers (hidden variables) is measured by observable variables of myopia, opportunistic behavior and over confidence of managers and the value content of accounting information (hidden variable) is evaluated by the observable variables of relevance of profit and relevance of book value. And reporting quality of financial information is also investigated based on the scores accrued to each company and the announcement published by the Tehran Stock Exchange based on the companies' rating in terms of the quality of reporting and proper notification. After insuring the acceptable fitness of the measurement pattern and the structure of research in both approaches; Structural Equations Modeling and regression, the results indicate that there is a significant negative relationship between the behavioral characteristics of managers and the reporting quality financial information. Also, there is a positive and significant relationship between value content of accounting information and reporting quality of financial information.