Session Name: | ML Tutorial Day: Beating Wallhacks using Deep Learning with Limited Resources |
Speaker(s): | Junsik Hwang |
Company Name(s): | Nexon Korea |
Track / Format: | Programming |
Did you know free users get access to 30% of content from the last 2 years?
Overview: | 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. |