Using deep learning to detect abusive sequences of member activity
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.
We have productionalized a deep learning model that operates directly on sequences of member requests in order to detect abusive automated activity.
To learn more about our modeling approach and how it addresses some unique challenges in the anti-abuse space, see this LinkedIn Engineering blog post.
Resources
Videos
Patents
- US Patent 11,936,682: DEEP LEARNING TO DETECT ABUSIVE SEQUENCES OF USER ACTIVITY IN ONLINE NETWORK
- US Patent 11,991,197: DEEP LEARNING USING ACTIVITY GRAPH TO DETECT ABUSIVE USER ACTIVITY IN ONLINE NETWORKS