In order to detect telecommunication frauds, most of the current approaches are based on labeling the caller numbers that are identified as frauds by customers. Since the telecommunication frauds cause severe financial loss to telecommunication customers, it is necessary and urgent to detect telecommunication frauds. Therefore, the Chinese government has built related departments and financed to help the research on telecommunication fraud detection (Li and Yuan 2017). At the same time, the telecommunications fraud detection became a hot topic. According to CNNIC (China Internet Network Information Center), the number of fraudulent calls reported by domestic users in 2015 reached 306 million times, which is 4.25 times that of 2014 (2015 China Mobile Internet Users’ Network Security Status Report, China Internet Network Information Center (CNNIC) 2016). According to the data released by the Ministry of Public Security, during the decade between 20, telecommunication fraud cases in China have been growing at a rapid rate of 20% to 30% every year, which have been grown rapidly especially in the past 5 years. Latest statistics in 2017 show that 90% of smartphone users in China have experienced telecommunication fraud (Facts 2017). If a person’s privacy is held by attackers, he could be the target of telecommunication frauds. With the development of the Internet, while people are enjoying various kinds of services from the Internet, their private information is gradually leaked out. Our results show that we can protect customers effectively. When an incoming fraud call is answered, the application can dynamically analyze the contents of the call in order to identify frauds.
#Doctors in training step 1 2015 download android
To achieve online detection of telecommunication frauds, we develop an Android application which can be installed on a customer’s smartphone. After that, we build rules to identify similar contents within the same call for further telecommunication fraud detection. Then we leverage natural language processing to extract features from the textual data. We use machine learning algorithms to analyze data and to select the high-quality descriptions from the data collected previously to construct datasets. Particularly, we collect descriptions of telecommunication fraud from news reports and social media. To solve this problem, we detect telecommunication frauds from the contents of a call instead of simply through the caller’s telephone number. However, attackers can simply evade such detection by changing their numbers, which is very easy to achieve through VoIP (Voice over IP). Traditional approaches to detect telecommunication frauds usually rely on constructing a blacklist of fraud telephone numbers. Telecommunication fraud has continuously been causing severe financial loss to telecommunication customers in China for several years.
0 kommentar(er)
