This article does not cite any sources. (March 2009) (Learn how and when to remove this template message)
In information security, intruder detection is the process of detecting intruders behind attacks as unique persons. This technique tries to identify the person behind an attack by analyzing their computational behaviour. This concept is sometimes confused with Intrusion Detection (also known as IDS) techniques which are the art of detecting intruder actions.
Some other earlier works reference the concept of Intruder Authentication, Intruder Verification, or Intruder Classification, but the Si6 project was one of the first projects to deal with the full scope of the concept.
Intruder Detection Systems try to detect who is attacking a system by analyzing his or her computational behaviour or biometric behaviour.
Some of the parameters used to identify a intruder
- Keystroke Dynamics (aka keystroke patterns, typing pattern, typing behaviour)
- Patterns using an interactive command interpreter:
- Commands used
- Commands sequence
- Accessed directories
- Character deletion
- Patterns on the network usage:
- IP address used
- Ports used
- TTL analysis
- Operating system used to attack
- Protocols used
- Connection times patterns
- IP address used
Keystroke dynamics is paramount in Intruder Detection techniques because it is the only parameter that has been classified as a real 'behavioural biometric pattern'.
Keystroke dynamics analyze times between keystrokes issued in a computer keyboard or cellular phone keypad searching for patterns. First techniques used statistics and probability concepts like 'standard deviations' and 'Mean', later approaches use data mining, neural networks, Support Vector Machine, etc.
There is a confusion with the Spanish translation of 'Intrusion detection system', also known as IDS. Some people translate it as 'Sistemas de Detección de Intrusiones', but others translate it as 'Sistemas de Detección de Intrusos'. Only the former is correct.