SDMP: A secure detector for epidemic disease file based on DNN

Abstract In the era of intelligent office, reading and processing PDF files by mobile devices have become important parts of various businesses. However, due to the universality of mobile device and PDF file, they are also often used by attackers to disguise malicious codes, which makes users in danger. Especially in medical field, once computer virus invades medical experts’ devices, a large number of data with high medical research value will face huge damage and irreparable loss. Therefore, how to ensure the security when users make use of PDF files is a challenging and meaningful task. In this paper, we design an secure detector of malicious PDF file for epidemic disease file based on Deep Neural Network to solve the problem of privacy and security in handling epidemic disease file. Experiment shows that the detection accuracy of our detector can achieve up to 99.3%. Moreover, the time cost on raining and forecasting of the proposed DNN model is extremely low, less than 1s per epoch.