The Multi-Agent Ranking framework (MARk) aims to provide all the building blocks that are required to build large scale detection and ranking systems. Namely, the framework provides the following key components:
All these components are implemented in a generic way. They are independent of the type of data that will be processed by the framework. This allows the data scientist to focus on his core business: developing effective detection algorithms.
Detecting suspicious or malicious activity in a network is not a trivial task. In recent years the attacks perpetrated have grown in sophistication and frequency. For this reason a new detection tool was developed, in the form of the Multi Agent Ranking framework (MARk). MARk sets the groundwork for the implementation of large scale detection and ranking systems through the implementation of a distributed storage in conjuncture with highly specialized, stand-alone detector agents. The detector agents are responsible for analyzing specific predefined characteristics and producing a report of any suspicious activity encountered.Read more
The Multi-Agent Ranking framework (MARk) is a generic server that allows to easily build large scale detection and ranking systems. It provides a web interface, a distributed execution framework for detection algorithms, storage for data and detection results, and an easy to configure triggering mechanism.Read more
In previous blog posts we showed how to inject a stream of data in the Multi-Agent Ranking framework, and how to use the built-in detectors to produce a ranking. This time we show how to implement your own detection algorithms.Read more
The Multi-Agent Ranking framework (MARk) aims to provide all the building blocks that are required to build large scale detection and ranking systems. For this blog post we will use docker and docker-compose to run a MARk server, then we will use PHP and composer to inject data in the framework.Read more