View, browse and sort the ever-growing list of sessions by pass type, track, and format. With this Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App, once live. Sessions do fill up so please arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.
Junsik Hwang (Machine Learning Engineer, Nexon Korea)
Pass Type: All Access, GDC Conference + Summits, GDC Summits - Get your pass now!
Tutorials: ML Tutorial Day
Vault Recording: Video
Audience Level: All
Albeit having compelling performance, deep learning requires an extensive database and massive computing power, and therefore considerable investment. In this session, Junsik will present how Nexon Korea has developed a real-time automated wallhack detection system using Convolutional Neural Networks with a small dataset and a single GPU. By using Class Activation Maps, the network finds suspicious areas within a screenshot that improves the credibility of the model's performance and makes debugging datasets much more efficient. Model Interpretability plays a crucial role in incorporating deep learning with the existing abuser control policies. As a result, the system now detects abusers in real-time and reduces manual inspection labor significantly.
Attendees will walk away from this session with practical tips on how to build a wallhack detection system using deep learning for their services even with a limited dataset and trust.
This session is intended for anyone who is interested in deep learning and its practical usage.