Applied Mathematics Seminar: Dynamic Fraud Detection via Sequential Modeling

Speaker: Shuhan Yuan, Computer Science Department, USU
Abstract: Due to the openness and anonymity of the Internet, online platforms (e.g., online social media or knowledge bases) attract a large number of malicious users, such as vandals, trolls, and hoaxes. These malicious users impose severe security threats to online platforms and their legitimate participants. For example, the fraudsters on Twitter can easily spread fake information or post harmful links on the platform. Deep learning models have achieved promising results in image, text, and speech recognition. The key ingredient for the success of deep learning is because it learns meaningful representations of inputs. However, it is challenging to develop deep learning models for fraud detection. In this talk, I focus on tackling two challenges, lack of labeled training data and how to model physical time for fraud detection.