Build Better Defenses
October 29–30, 2017: Training
October 30–November 1, 2017: Tutorials & Conference
New York, NY

Inside the bad actor's studio

Julian Wong (DataVisor)
11:20am–12:00pm Tuesday, October 31, 2017
Security analytics
Location: Sutton North
Average rating: ****.
(4.00, 1 rating)

Who is this presentation for?

  • Executives and managers focused on data science and security who are concerned about or being tasked with fraud detection

Prerequisite knowledge

  • A general understanding of big data technologies, such as Spark

What you'll learn

  • Understand the most sophisticated attack motivations and techniques currently in use by online criminals around the globe
  • Explore detailed examples of attacks on various online services, including financial, ecommerce, social networking, gaming, and other market verticals
  • Learn why these modern attacks are difficult to detect and what can be done about it
  • Discover how real-time in-memory big data analytics, unsupervised machine learning, and AI can be used to find patterns in data to uncover and stop online criminals

Description

The amount of user data being processed on any given day is astronomical and can overwhelm even the most seasoned security teams. Today’s most innovative online criminals know how to take advantage of a company’s inability to focus on anything except anomalies and blend in among the masses. Well-organized crime rings exploit the latest breaches, stolen identities, and free tools to create millions of fake accounts to hide among billions of benign users of your service, and they are waging a variety of large-scale attacks to exploit these services for financial gain.

Using research from more than one billion users, 500 billion events, and 50 million malicious accounts collected from global online services, Julian Wong details some of the sophisticated attack techniques being used by modern day online criminals to evade detection, including hiding locations through VPNs and cloud-hosting services, mobile device flashing, and faking browser info, user-agent strings, and MAC addresses. Julien then uses this data to provide context for how complex the detection challenges being faced by security teams are and demonstrates how these types of attacks can be detected and mitigated by leveraging the latest in artificial intelligence, including Spark-based big data security analytics and unsupervised machine learning.

Photo of Julian Wong

Julian Wong

DataVisor

Julian Wong is an architect at DataVisor. A fraud and security detection industry veteran, Julien was previously head of trust and safety at Indiegogo and Etsy; risk management leader at Upwork, where he developed scalable systems and teams for mitigating fraud and risks; and the lead for Google’s engineering team responsible for building algorithms to prevent fraud on its ad platform. Julian holds a bachelor’s degree in engineering from the University of California, Berkeley, and an MBA from NYU’s Stern School of Business.