From the course: Artificial Intelligence for Cybersecurity
Join today to access over 23,200 courses taught by industry experts.
Prediction by regression
From the course: Artificial Intelligence for Cybersecurity
Prediction by regression
- [Instructor] A quite common need in security space is to predict a future event based on the known data at hand. Let's take two examples. Your goal is to predict the count of IoT devices deployed in the field that may be tampered with during an attack. You want to build a machine learning model by using captured network packets and sensor data emitted from these devices over a period of time. In a second example, you have an ongoing distributed denial of service attack in your network and you want to predict the short term intensity and the impact of this attack. Of course, you do have access to ICMP, SIN, and other types of network packets to create your label data. Such prediction problems fall under the broad category of so-called regression problems. By identifying your problem as a regression problem, you automatically narrow down the list of algorithms that you must choose from. Regression algorithms attempt to build…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.