**Please note: This competition ends at 12/4/2023 5:59 AM UTC (Universal Coordinated Time), which is 12/3/2023 at 11:59pm**
Can machine learning identify when a network connection or intrusion is malicious? Network security is a universal concern. And, as attack mechanisms became more sophisticated, network security and identification mechanisms had to adopt newer strategies as well. This classroom challenge will introduce you to tackling network security issues with machine learning.
Machine learning is used in a variety of security fronts. It’s used to detect malicious activity and stop attacks, analyze mobile endpoints, enhance human analysis, automate repetitive security tasks, and close zero-day vulnerabilities.
MIT’s Lincoln Labs, as part of the 1998 Darpa Intrusion Detection Evaluation Program, set up an environment to acquire nine weeks of raw TCP data dumps for a local area network (LAN) simulating a typical U.S Air Force LAN. They operated the LAN in a manner comparable to a true Air Force environment except they peppered the LAN with numerous attacks. This labeled data is what you’ll be working with as you try to tackle network security.
In this competition, you’ll build algorithms to identify if a connection is normal or part of a malicious attack. You’ll be building a multi-class classification model leveraging the network data provided by Lincoln Labs. Winning models will be sure to carefully consider feature engineering along with model selection to create flexible models able to handle varied network traffic.
To be successful in this competition, you will need to build a machine learning classifier capable of identifying the type of connection and what type of traffic it is: normal or malicious. Along the way, you’ll gain familiarity with exploratory data analysis, data cleaning and preparation, feature engineering, model selection, and hyper parameter tuning.
Acknowledgements
We thank the MIT Lincoln Lab & KDD.