Mass Production of Functional Amine–Conjugated PAN Nanofiber Mat via Syringeless Electrospinning and CVD

Polymeric nanofiber webs have attained much attention because they can provide high surface area with various functional groups. To obtain the polymeric nanofiber webs, electrospinning is the most attractive method because this can provide the versatility of material selection. However, it is relatively difficult to obtain the nanofiber webs, which have highly reactive functional groups and high mechanical strength with high production rate. Here, the helically probed rotating cylinder (HPRC) system based on syringeless electrospinning and chemical vapor deposition (CVD) is introduced to prepare the polyacrylonitrile (PAN) nanofiber webs, having high functional groups and high mechanical strength in fast production rate. The HPRC system can provide the PAN nanofiber webs in high production rate, and the CVD process can provide high reactive functional groups on the PAN nanofiber. In addition, the nanofiber webs can be applied to diverse potential application fields, which require a high number of functional moieties.     

MAPAS: a practical deep learning-based android malware detection system

A lot of malicious applications appears every day, threatening numerous users. Therefore, a surge of studies have been conducted to protect users from newly emerging malware by using machine learning algorithms. Albeit existing machine or deep learning-based Android malware detection approaches achieve high accuracy by using a combination of multiple features, it is not possible to employ them on our mobile devices due to the high cost for using them. In this paper, we propose MAPAS, a malware detection system, that achieves high accuracy and adaptable usages of computing resources. MAPAS analyzes behaviors of malicious applications based on API call graphs of them by using convolution neural networks (CNN). However, MAPAS does not use a classifier model generated by CNN, it only utilizes CNN for discovering common features of API call graphs of malware. For efficiently detecting malware, MAPAS employs a lightweight classifier that calculates a similarity between API call graphs used for malicious activities and API call graphs of applications that are going to be classified. To demonstrate the effectiveness and efficiency of MAPAS, we implement a prototype and thoroughly evaluate it. And, we compare MAPAS with a state-of-the-art Android malware detection approach, MaMaDroid. Our evaluation results demonstrate that MAPAS can classify applications 145.8% faster and uses memory around ten times lower than MaMaDroid. Also, MAPAS achieves higher accuracy (91.27%) than MaMaDroid (84.99%) for detecting unknown malware. In addition, MAPAS can generally detect any type of malware with high accuracy.