Online fraud flourishes as online services become ubiquitous in our daily life. Malicious activities are present in industries ranging from social networks, dating apps, ecommerce websites, and mobile games to credit card agencies, online banks, and insurance companies. Fraudsters create fake accounts or take over existing user accounts and use them to write fake product reviews, send false information to other users, pretend to sell nonexistent products, spend money from stolen credit cards, and file fake insurance claims. To make such efforts economically viable, fraudsters almost always act in a coordinated fashion, meaning that they create a large amount of fake accounts to carry out their attacks.
Fang Yu explains how leading fraud detection company DataVisor leverages cutting-edge deep learning technologies to address the challenges in large-scale fraud detection. The company’s technology uses a customized model that improves upon standard convolutional neural networks (CNN) and achieves competitive results.
Fang Yu is the cofounder and CTO of DataVisor, where her work focuses on big data for security. Over the past 10 years, Fang has developed algorithms and built systems for identifying various kinds of malicious traffic including worms, spam, bot queries, faked and hijacked account activities, and fraudulent financial transactions. Fang holds a PhD degree from the EECS Department at the University of California, Berkeley.
Comments on this page are now closed.
©2019, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com