The advance of smartphones and cellular networks boosts the need of mobileadvertising and targeted marketing. However, it also triggers the unseensecurity threats. We found that the phone scams with fake calling numbers ofvery short lifetime are increasingly popular and have been used to trick theusers. The harm is worldwide. On the other hand, deceptive advertising(deceptive ads), the fake ads that tricks users to install unnecessary apps viaeither alluring or daunting texts and pictures, is an emerging threat thatseriously harms the reputation of the advertiser. To counter against these twonew threats, the conventional blacklist (or whitelist) approach and the machinelearning approach with predefined features have been proven useless.Nevertheless, due to the success of deep learning in developing the highlyintelligent program, our system can efficiently and effectively detect phonescams and deceptive ads by taking advantage of our unified framework on deepneural network (DNN) and convolutional neural network (CNN). The proposedsystem has been deployed for operational use and the experimental resultsproved the effectiveness of our proposed system. Furthermore, we keep ourresearch results and release experiment material onhttp://DeceptiveAds.TWMAN.ORG and http://PhoneScams.TWMAN.ORG if there is anyupdate.
展开▼