Scale Events
+00:00 GMT
LIVESTREAM
Using Deep Learning to Detect Abusive Sequences of Member Activity on LinkedIn

The Anti-Abuse AI Team at LinkedIn creates, deploys, and maintains models that detect and prevent many types of abuse, including the creation of fake accounts, member profile scraping, automated spam, and account takeovers. Bad actors use automation to scale their attempted abuse.

There are many unique challenges associated with using machine learning to stop abuse on a large professional network including maximizing signal, keeping up with adversarial attackers, and covering many heterogeneous attack surfaces. In addition, traditional machine learning models require hand-engineered features that are often specific to a particular type of abuse and attack surface. To address these challenges, we have productionalized a deep learning model that operates directly on raw sequences of member activity, allowing us to scalably leverage more of the available signal hidden in the data and stop adversarial attacks more effectively. Our first production use case of this model was the detection of logged-in accounts scraping member profile data.

We will present results demonstrating the promise of this modeling approach and discuss how it helps to solve many of the unique challenges in the anti-abuse domain.

Speakers
James Verbus
James Verbus
Staff Machine Learning Engineer @ LinkedIn
Agenda
Track View
8:00 PM, GMT
-
8:45 PM, GMT
Stage 1
Presentation
Using Natural Language Processing (NLP) to Classify User Behavior Activity Streams, with LinkedIn

The Anti-Abuse AI Team at LinkedIn creates, deploys, and maintains models that detect and prevent many types of abuse, including the creation of fake accounts, member profile scraping, automated spam, and account takeovers. To address these challenges, LinkedIn has deployed a deep learning model that operates directly on raw sequences of member activity, allowing them to scalably leverage more of the available signal hidden in the data. This helps them stop adversarial attacks more effectively. Their first production use case of this model was the detection of logged-in accounts scraping member profile data. In this session, James Verbus, Staff Machine Learning Engineer at LinkedIn, will describe the MLP techniques LinkedIn uses to detect malicious behavior in streams of user activity data.

+ Read More
James Verbus
Event has finished
November 09, 8:00 PM, GMT
Online
Event has finished
November 09, 8:00 PM, GMT
Online